{ "openapi": "3.1.0", "info": { "title": "Gladia Enterprise API", "version": "2", "description": "Real-time speech-to-text: open a session, stream audio over a WebSocket, receive transcripts as they are spoken." }, "servers": [ { "url": "https://{cluster}.api.gladia.io", "variables": { "cluster": { "default": "eu1", "description": "Your region's endpoint, as shown in Gladia Workspace." } } } ], "security": [ { "apiKey": [] } ], "tags": [ { "name": "Live", "description": "Real-time transcription sessions." } ], "paths": { "/v2/live": { "post": { "operationId": "initLiveSession", "summary": "Initiate a session", "description": "Creates a live session with its options and returns the WebSocket URL to stream its audio to.", "tags": [ "Live" ], "parameters": [ { "name": "region", "in": "query", "required": false, "description": "Where the audio is processed. Every endpoint processes it in its own region (eu1: Europe, us1: United States); a region the endpoint does not serve finds no model and the session is refused.", "schema": { "type": "string", "enum": [ "eu", "us", "eu-west", "us-west" ] } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LiveInitRequest" }, "example": { "encoding": "wav/pcm", "sample_rate": 16000, "bit_depth": 16, "channels": 1, "model": "solaria-3", "language_config": { "languages": [ "en" ] }, "messages_config": { "receive_partial_transcripts": true } } } } }, "responses": { "201": { "description": "The session is created.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InitResponse" } } } }, "400": { "description": "The request is invalid: `validation_errors` lists why.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "402": { "description": "Your workspace has no credits left (`insufficient_credits`): new sessions are refused until credits are added; sessions already running are not stopped.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Your account already has its maximum number of open sessions.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "500": { "description": "No model in this region runs the session as asked (its model, languages and features together), or none has room right now: `no inference endpoint available`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "The service cannot answer right now: try again.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl -X POST https://eu1.api.gladia.io/v2/live \\\n -H \"x-gladia-key: $GLADIA_API_KEY\" \\\n -H \"content-type: application/json\" \\\n -d '{\n \"encoding\": \"wav/pcm\",\n \"sample_rate\": 16000,\n \"bit_depth\": 16,\n \"channels\": 1,\n \"model\": \"solaria-3\",\n \"language_config\": {\n \"languages\": [\n \"en\"\n ]\n },\n \"messages_config\": {\n \"receive_partial_transcripts\": true\n }\n }'" }, { "lang": "python", "label": "Python", "source": "import os\n\nimport requests\n\nAPI_URL = os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\")\nresponse = requests.post(\n f\"{API_URL}/v2/live\",\n headers={\"x-gladia-key\": os.environ[\"GLADIA_API_KEY\"]},\n json={\n \"encoding\": \"wav/pcm\",\n \"sample_rate\": 16000,\n \"bit_depth\": 16,\n \"channels\": 1,\n \"model\": \"solaria-3\",\n \"language_config\": {\n \"languages\": [\n \"en\"\n ]\n },\n \"messages_config\": {\n \"receive_partial_transcripts\": True\n }\n },\n timeout=10,\n)\nresponse.raise_for_status()\nprint(response.json())" }, { "lang": "js", "label": "JavaScript", "source": "const API_URL = process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\";\nconst response = await fetch(`${API_URL}/v2/live`, {\n method: \"POST\",\n headers: {\n \"x-gladia-key\": process.env.GLADIA_API_KEY,\n \"content-type\": \"application/json\",\n },\n body: JSON.stringify({\n \"encoding\": \"wav/pcm\",\n \"sample_rate\": 16000,\n \"bit_depth\": 16,\n \"channels\": 1,\n \"model\": \"solaria-3\",\n \"language_config\": {\n \"languages\": [\n \"en\"\n ]\n },\n \"messages_config\": {\n \"receive_partial_transcripts\": true\n }\n }),\n});\nif (!response.ok) {\n throw new Error(`${response.status} ${await response.text()}`);\n}\nconsole.log(await response.json());" } ] }, "get": { "operationId": "listLiveSessions", "summary": "List sessions", "description": "Your account's sessions, newest first, one page at a time.", "tags": [ "Live" ], "parameters": [ { "name": "limit", "in": "query", "description": "Sessions per page, at most 100.", "schema": { "type": "integer", "minimum": 1, "maximum": 100, "default": 20 } }, { "name": "offset", "in": "query", "description": "Sessions to skip, at most 1000; past that, follow `next`.", "schema": { "type": "integer", "minimum": 0, "maximum": 1000, "default": 0 } }, { "name": "cursor", "in": "query", "description": "Where the next page starts: set in `next`, never by hand.", "schema": { "type": "string" } }, { "name": "date", "in": "query", "description": "Only the sessions created that day (`2026-10-12`).", "schema": { "type": "string", "format": "date" } }, { "name": "after_date", "in": "query", "description": "Only the sessions created after that date (ISO 8601).", "schema": { "type": "string", "format": "date-time" } }, { "name": "before_date", "in": "query", "description": "Only the sessions created before that date (ISO 8601).", "schema": { "type": "string", "format": "date-time" } }, { "name": "status", "in": "query", "description": "Only the sessions with these statuses (repeat it for several).", "schema": { "type": "array", "items": { "type": "string", "enum": [ "queued", "processing", "done", "error" ] } }, "style": "form", "explode": true }, { "name": "custom_metadata", "in": "query", "description": "Only the sessions whose `custom_metadata` has these values: a JSON object (`{\"user\": \"john\"}`), or `custom_metadata[user]=john`.", "schema": { "type": "string" } } ], "responses": { "200": { "description": "A page of sessions.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LiveSessionList" } } } }, "400": { "description": "The request is invalid: `validation_errors` lists why.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "The service cannot answer right now: try again.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl https://eu1.api.gladia.io/v2/live \\\n -H \"x-gladia-key: $GLADIA_API_KEY\"" }, { "lang": "python", "label": "Python SDK", "source": "import os\n\nfrom gladiaio_sdk import GladiaClient\n\nclient = GladiaClient(\n api_key=os.environ[\"GLADIA_API_KEY\"],\n api_url=os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\"),\n)\n\npage = client.live_v2().list({\"limit\": 20, \"status\": [\"done\"]})\nfor session in page.items:\n print(session.id, session.created_at)" }, { "lang": "js", "label": "JavaScript SDK", "source": "import { GladiaClient } from \"@gladiaio/sdk\";\n\nconst client = new GladiaClient({\n apiKey: process.env.GLADIA_API_KEY,\n apiUrl: process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\",\n});\n\nconst page = await client.liveV2().list({ limit: 20, status: [\"done\"] });\nfor (const session of page.items) console.log(session.id, session.created_at);" } ] } }, "/v2/live/defaults": { "get": { "operationId": "getLiveDefaults", "summary": "Get the defaults", "description": "The value each option gets when the init body omits it.", "tags": [ "Live" ], "responses": { "200": { "description": "The defaults in force.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/SessionDefaults" } } } }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl https://eu1.api.gladia.io/v2/live/defaults \\\n -H \"x-gladia-key: $GLADIA_API_KEY\"" }, { "lang": "python", "label": "Python", "source": "import os\n\nimport requests\n\nAPI_URL = os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\")\nresponse = requests.get(\n f\"{API_URL}/v2/live/defaults\",\n headers={\"x-gladia-key\": os.environ[\"GLADIA_API_KEY\"]},\n timeout=10,\n)\nresponse.raise_for_status()\nprint(response.json())" }, { "lang": "js", "label": "JavaScript", "source": "const API_URL = process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\";\nconst response = await fetch(`${API_URL}/v2/live/defaults`, {\n headers: {\n \"x-gladia-key\": process.env.GLADIA_API_KEY,\n \"content-type\": \"application/json\",\n },\n});\nif (!response.ok) {\n throw new Error(`${response.status} ${await response.text()}`);\n}\nconsole.log(await response.json());" } ] } }, "/v2/live/capabilities": { "get": { "operationId": "getLiveCapabilities", "summary": "Get the capabilities", "description": "The models, and per model the add-ons, that `POST /v2/live` accepts for your key right now. Nothing is created. A model or add-on that no inference endpoint open to you can take at the moment (busy, down, not enabled) is left out.", "tags": [ "Live" ], "responses": { "200": { "description": "The models and add-ons you can ask for.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LiveCapabilities" } } } }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl https://eu1.api.gladia.io/v2/live/capabilities \\\n -H \"x-gladia-key: $GLADIA_API_KEY\"" }, { "lang": "python", "label": "Python", "source": "import os\n\nimport requests\n\nAPI_URL = os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\")\nresponse = requests.get(\n f\"{API_URL}/v2/live/capabilities\",\n headers={\"x-gladia-key\": os.environ[\"GLADIA_API_KEY\"]},\n timeout=10,\n)\nresponse.raise_for_status()\nprint(response.json())" }, { "lang": "js", "label": "JavaScript", "source": "const API_URL = process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\";\nconst response = await fetch(`${API_URL}/v2/live/capabilities`, {\n headers: {\n \"x-gladia-key\": process.env.GLADIA_API_KEY,\n \"content-type\": \"application/json\",\n },\n});\nif (!response.ok) {\n throw new Error(`${response.status} ${await response.text()}`);\n}\nconsole.log(await response.json());" } ] } }, "/v2/live/{id}": { "get": { "operationId": "getLiveSession", "summary": "Get a session", "description": "A session's status and options and, once it ended, its transcript.", "tags": [ "Live" ], "parameters": [ { "name": "id", "in": "path", "required": true, "description": "Identifier of the session (`id` of `POST /v2/live`).", "schema": { "type": "string", "format": "uuid" } } ], "responses": { "200": { "description": "The session.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/LiveSession" } } } }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "404": { "description": "No such session for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "The service cannot answer right now: try again.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl https://eu1.api.gladia.io/v2/live/0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b \\\n -H \"x-gladia-key: $GLADIA_API_KEY\"" }, { "lang": "python", "label": "Python SDK", "source": "import os\n\nfrom gladiaio_sdk import GladiaClient\n\nclient = GladiaClient(\n api_key=os.environ[\"GLADIA_API_KEY\"],\n api_url=os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\"),\n)\n\nsession = client.live_v2().get(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\")\nprint(session.status, session.result)" }, { "lang": "js", "label": "JavaScript SDK", "source": "import { GladiaClient } from \"@gladiaio/sdk\";\n\nconst client = new GladiaClient({\n apiKey: process.env.GLADIA_API_KEY,\n apiUrl: process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\",\n});\n\nconst session = await client.liveV2().get(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\");\nconsole.log(session.status, session.result);" } ] }, "delete": { "operationId": "deleteLiveSession", "summary": "Delete a session", "description": "Deletes a session that has ended, its transcript and its recording.", "tags": [ "Live" ], "parameters": [ { "name": "id", "in": "path", "required": true, "description": "Identifier of the session (`id` of `POST /v2/live`).", "schema": { "type": "string", "format": "uuid" } } ], "responses": { "202": { "description": "Deleted." }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The session is still running.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "404": { "description": "No such session for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "The service cannot answer right now: try again.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl -X DELETE https://eu1.api.gladia.io/v2/live/0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b \\\n -H \"x-gladia-key: $GLADIA_API_KEY\"" }, { "lang": "python", "label": "Python SDK", "source": "import os\n\nfrom gladiaio_sdk import GladiaClient\n\nclient = GladiaClient(\n api_key=os.environ[\"GLADIA_API_KEY\"],\n api_url=os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\"),\n)\n\nclient.live_v2().delete(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\")\nprint(\"deleted\")" }, { "lang": "js", "label": "JavaScript SDK", "source": "import { GladiaClient } from \"@gladiaio/sdk\";\n\nconst client = new GladiaClient({\n apiKey: process.env.GLADIA_API_KEY,\n apiUrl: process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\",\n});\n\nawait client.liveV2().delete(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\");\nconsole.log(\"deleted\");" } ] } }, "/v2/live/{id}/file": { "get": { "operationId": "getLiveSessionAudio", "summary": "Download the audio", "description": "The session's recording, in FLAC, for accounts that record their audio. Available about 40 seconds after the session ends. A `Range` header returns part of it.", "tags": [ "Live" ], "parameters": [ { "name": "id", "in": "path", "required": true, "description": "Identifier of the session (`id` of `POST /v2/live`).", "schema": { "type": "string", "format": "uuid" } } ], "responses": { "200": { "description": "The recording.", "content": { "audio/flac": { "schema": { "type": "string", "format": "binary" } } } }, "206": { "description": "The requested range of the recording." }, "302": { "description": "A redirect to a signed download URL." }, "401": { "description": "No API key, or an unknown one.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "The key may not do this (its scopes, or the addresses it may be used from).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "404": { "description": "No such session for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "The service cannot answer right now: try again.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "x-codeSamples": [ { "lang": "bash", "label": "curl", "source": "curl -L https://eu1.api.gladia.io/v2/live/0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b/file \\\n -H \"x-gladia-key: $GLADIA_API_KEY\" \\\n -o session.flac" }, { "lang": "python", "label": "Python SDK", "source": "import os\n\nfrom gladiaio_sdk import GladiaClient\n\nclient = GladiaClient(\n api_key=os.environ[\"GLADIA_API_KEY\"],\n api_url=os.environ.get(\"GLADIA_API_URL\", \"https://eu1.api.gladia.io\"),\n)\n\naudio = client.live_v2().get_file(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\")\nwith open(\"session.flac\", \"wb\") as file:\n file.write(audio)" }, { "lang": "js", "label": "JavaScript SDK", "source": "import { writeFileSync } from \"node:fs\";\nimport { GladiaClient } from \"@gladiaio/sdk\";\n\nconst client = new GladiaClient({\n apiKey: process.env.GLADIA_API_KEY,\n apiUrl: process.env.GLADIA_API_URL ?? \"https://eu1.api.gladia.io\",\n});\n\nconst audio = await client.liveV2().getFile(\"0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b\");\nwriteFileSync(\"session.flac\", Buffer.from(audio));" } ] } } }, "x-websocket": { "url": "wss://{cluster}.api.gladia.io/v2/live?token={token}", "description": "The `url` of `POST /v2/live`. Send the audio as binary frames, or as `audio_chunk` messages; send `stop_recording` when done. The server sends the messages below, then closes the connection.", "client_messages": [ { "$ref": "#/components/schemas/AudioChunkAction" }, { "$ref": "#/components/schemas/StopRecordingAction" } ], "server_messages": [ { "$ref": "#/components/schemas/StartRecordingMessage" }, { "$ref": "#/components/schemas/TranscriptMessage" }, { "$ref": "#/components/schemas/SpeechStartMessage" }, { "$ref": "#/components/schemas/SpeechEndMessage" }, { "$ref": "#/components/schemas/NamedEntityRecognitionMessage" }, { "$ref": "#/components/schemas/PiiMessage" }, { "$ref": "#/components/schemas/SentimentAnalysisMessage" }, { "$ref": "#/components/schemas/TranslationMessage" }, { "$ref": "#/components/schemas/EndOfTurnMessage" }, { "$ref": "#/components/schemas/AudioChunkAckMessage" }, { "$ref": "#/components/schemas/StopRecordingAckMessage" }, { "$ref": "#/components/schemas/EndRecordingMessage" }, { "$ref": "#/components/schemas/PostTranscriptMessage" }, { "$ref": "#/components/schemas/PostFinalTranscriptMessage" }, { "$ref": "#/components/schemas/EndSessionMessage" }, { "$ref": "#/components/schemas/ErrorMessage" } ], "delivery": { "start_recording": { "flags": [ "receive_lifecycle_events" ], "callback": true }, "transcript": { "flags": [ "receive_partial_transcripts", "receive_final_transcripts" ], "callback": true }, "speech_start": { "flags": [ "receive_speech_events" ], "callback": true }, "speech_end": { "flags": [ "receive_speech_events" ], "callback": true }, "named_entity_recognition": { "flags": [ "receive_realtime_processing_events" ], "callback": true }, "pii": { "flags": [], "callback": false }, "sentiment_analysis": { "flags": [ "receive_realtime_processing_events" ], "callback": true }, "translation": { "flags": [ "receive_realtime_processing_events" ], "callback": true }, "end_of_turn": { "flags": [], "callback": false }, "audio_chunk": { "flags": [ "receive_acknowledgments" ], "callback": true }, "stop_recording": { "flags": [ "receive_acknowledgments" ], "callback": true }, "end_recording": { "flags": [ "receive_lifecycle_events" ], "callback": true }, "post_transcript": { "flags": [ "receive_post_processing_events" ], "callback": true }, "post_final_transcript": { "flags": [ "receive_post_processing_events" ], "callback": true }, "end_session": { "flags": [ "receive_lifecycle_events" ], "callback": true }, "error": { "flags": [ "receive_errors" ], "callback": true }, "start_session": { "flags": [ "receive_lifecycle_events" ], "callback": true, "callback_only": true } }, "close_codes": { "1000": "The session ended normally.", "1011": "The session failed; its reason says why. `rejected: …`: an option the model refused (a translation target it does not serve, translation with PII redaction…): fix the init body and create a new session.", "1012": "The service is restarting: reconnect to the same URL to resume.", "4401": "Invalid or expired token." } }, "x-models": [ { "name": "solaria-3", "description": "Multilingual, with automatic language detection; the only model that translates.", "languages": [ "ar", "cs", "da", "de", "el", "en", "es", "fa", "fi", "fr", "hi", "hu", "id", "it", "ja", "ko", "mk", "ms", "nl", "pl", "pt", "ro", "ru", "sv", "th", "tl", "tr", "vi", "zh" ], "features": { "custom_vocabulary": true, "punctuation": true, "numerals": true, "named_entity_recognition": true, "pii": true, "end_of_turn": true, "number_hold": true, "sentiment_analysis": true, "diarization": true, "translation": true } }, { "name": "solaria-1", "description": "Gladia's multilingual model: 99 languages and Cantonese, detected or set.", "languages": [ "af", "am", "ar", "as", "az", "ba", "be", "bg", "bn", "bo", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fo", "fr", "gl", "gu", "ha", "haw", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jw", "ka", "kk", "km", "kn", "ko", "la", "lb", "ln", "lo", "lt", "lv", "mg", "mi", "mk", "ml", "mn", "mr", "ms", "mt", "my", "ne", "nl", "nn", "no", "oc", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "sn", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "tg", "th", "tk", "tl", "tr", "tt", "uk", "ur", "uz", "vi", "yi", "yo", "zh" ], "features": { "custom_vocabulary": true, "punctuation": true, "numerals": true, "named_entity_recognition": true, "pii": true, "end_of_turn": true, "number_hold": true, "sentiment_analysis": true, "diarization": true, "translation": false } }, { "name": "trantoria-1", "description": "The lowest latency: transcripts within a fraction of a second. About 40 languages, English and Spanish included: set the language spoken.", "languages": null, "features": { "custom_vocabulary": true, "punctuation": true, "numerals": true, "named_entity_recognition": true, "pii": true, "end_of_turn": true, "number_hold": true, "sentiment_analysis": true, "diarization": true, "translation": false } } ], "x-translation-targets": [ "af", "am", "ar", "as", "be", "bg", "bn", "ca", "da", "de", "en", "es", "fa", "fr", "gl", "id", "it", "ja", "km", "ko", "ln", "lo", "ms", "my", "ne", "nl", "no", "ps", "pt", "ro", "ru", "so", "sv", "th", "vi", "wo", "yo", "zh" ], "components": { "securitySchemes": { "apiKey": { "type": "apiKey", "in": "header", "name": "x-gladia-key", "description": "Your API key, from Gladia Workspace." } }, "schemas": { "AddonError": { "additionalProperties": false, "properties": { "message": { "type": "string" } }, "required": [ "message" ], "title": "AddonError", "type": "object" }, "AudioChunkAckData": { "additionalProperties": false, "properties": { "byte_range": { "description": "First and last byte (excluded) of the acknowledged audio, from the start of the session.", "items": { "type": "integer" }, "maxItems": 2, "minItems": 2, "type": "array" }, "time_range": { "description": "The same range in milliseconds.", "items": { "type": "integer" }, "maxItems": 2, "minItems": 2, "type": "array" } }, "required": [ "byte_range", "time_range" ], "title": "AudioChunkAckData", "type": "object" }, "AudioChunkAckMessage": { "additionalProperties": false, "description": "Audio transcribed: a client may drop it from its resend buffer\n(`receive_acknowledgments`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "audio_chunk", "type": "string" }, "acknowledged": { "type": "boolean" }, "error": { "$ref": "#/components/schemas/JsonValue", "default": null }, "data": { "$ref": "#/components/schemas/AudioChunkAckData" } }, "required": [ "session_id", "created_at", "type", "acknowledged", "data" ], "title": "AudioChunkAckMessage", "type": "object" }, "AudioChunkAction": { "additionalProperties": false, "description": "Audio, as JSON. Binary frames of raw audio are accepted too, and cost a third less.", "properties": { "type": { "const": "audio_chunk", "type": "string" }, "data": { "$ref": "#/components/schemas/AudioChunkPayload" } }, "required": [ "type", "data" ], "title": "AudioChunkAction", "type": "object" }, "AudioChunkPayload": { "additionalProperties": false, "properties": { "chunk": { "description": "Audio, base64-encoded, in the session's encoding.", "type": "string" } }, "required": [ "chunk" ], "title": "AudioChunkPayload", "type": "object" }, "CallbackConfig": { "additionalProperties": false, "properties": { "url": { "format": "uri", "minLength": 1, "type": "string", "description": "The HTTPS URL that receives the messages, one POST each." }, "receive_partial_transcripts": { "default": false, "type": "boolean", "description": "Partial transcripts." }, "receive_final_transcripts": { "default": true, "type": "boolean", "description": "Final transcripts." }, "receive_speech_events": { "default": false, "type": "boolean", "description": "`speech_start` and `speech_end`." }, "receive_pre_processing_events": { "default": true, "type": "boolean", "description": "Pre-processing messages." }, "receive_realtime_processing_events": { "default": true, "type": "boolean", "description": "Messages of the realtime processing." }, "receive_post_processing_events": { "default": true, "type": "boolean", "description": "`post_transcript` and `post_final_transcript`." }, "receive_acknowledgments": { "default": false, "type": "boolean", "description": "Acknowledgments." }, "receive_errors": { "default": false, "type": "boolean", "description": "`error` messages." }, "receive_lifecycle_events": { "default": true, "type": "boolean", "description": "`start_session`, `start_recording`, `end_recording` and `end_session`." } }, "required": [ "url" ], "title": "CallbackConfig", "type": "object" }, "CustomSpellingConfig": { "additionalProperties": false, "properties": { "spelling_dictionary": { "additionalProperties": { "items": { "type": "string" }, "type": "array" }, "type": "object", "description": "The spelling to write (key) for each variant heard (values): `{\"Gladia\": [\"gladya\", \"glad ia\"]}`. Whole words, case-insensitive." } }, "required": [ "spelling_dictionary" ], "title": "CustomSpellingConfig", "type": "object" }, "CustomVocabularyConfig": { "additionalProperties": false, "properties": { "vocabulary": { "items": { "anyOf": [ { "type": "string" }, { "$ref": "#/components/schemas/VocabularyItem" } ] }, "type": "array", "description": "Words or phrases, as strings or as objects with their own options." }, "default_intensity": { "anyOf": [ { "maximum": 1, "minimum": 0, "type": "number" }, { "type": "null" } ], "default": null, "description": "How strongly the words are favoured, from 0 to 1, when an entry sets none." } }, "required": [ "vocabulary" ], "title": "CustomVocabularyConfig", "type": "object" }, "DiarizationConfig": { "title": "DiarizationConfig", "type": "object", "additionalProperties": false, "properties": { "number_of_speakers": { "type": "integer", "minimum": 1, "description": "Expected number of speakers, when you know it." }, "max_speakers": { "type": "integer", "minimum": 1, "description": "Highest number of speakers to tell apart." } } }, "EndOfTurnConfig": { "additionalProperties": false, "description": "`end_of_turn` options (extension): each key overrides the gateway's live default\n(`END_OF_TURN_DEFAULTS`), then the engine's (RTASR_EOT_*). The engine's own bounds\n(inference/rtasr/core/endpointing/eot.py), checked here so a bad value is a 400 on the init\ninstead of a refused WebSocket.", "properties": { "threshold": { "anyOf": [ { "exclusiveMaximum": 1, "exclusiveMinimum": 0, "type": "number" }, { "type": "null" } ], "default": null, "description": "End-of-turn probability, between 0 and 1 (excluded), above which the turn ends." }, "silence_ms": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 10000, "type": "integer" }, { "type": "null" } ], "default": null, "description": "Silence, in milliseconds, before a turn is evaluated." }, "stop_s": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 60, "type": "number" }, { "type": "null" } ], "default": null, "description": "Silence, in seconds, that ends the turn whatever the probability." }, "emit_scores": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null, "description": "Also send an `end_of_turn_score` message for each evaluation, to calibrate `threshold`." }, "window_s": { "anyOf": [ { "exclusiveMinimum": 0, "maximum": 8, "type": "number" }, { "type": "null" } ], "default": null, "description": "Audio, in seconds, an evaluation reads before the silence (at most 8)." }, "speech_dbfs": { "anyOf": [ { "maximum": 0, "minimum": -100, "type": "number" }, { "type": "null" } ], "default": null, "description": "Level, in dBFS, under which audio counts as silence." }, "reeval_ms": { "anyOf": [ { "maximum": 10000, "minimum": 0, "type": "integer" }, { "type": "null" } ], "default": null, "description": "Interval, in milliseconds, between two evaluations of the same silence." } }, "title": "EndOfTurnConfig", "type": "object" }, "EndOfTurnData": { "additionalProperties": false, "properties": { "channel": { "type": "integer" }, "probability": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Probability that the speaker finished." }, "reason": { "anyOf": [ { "enum": [ "model", "timeout" ], "type": "string" }, { "type": "null" } ], "description": "`model`: the end-of-turn probability crossed `threshold`; `timeout`: the silence reached `stop_s`." }, "end": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "When the turn ended, in seconds." }, "speech_duration": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Speech in the turn, in seconds." } }, "required": [ "channel", "probability", "reason", "end", "speech_duration" ], "title": "EndOfTurnData", "type": "object" }, "EndOfTurnDefaults": { "additionalProperties": false, "properties": { "threshold": { "description": "End-of-turn probability above which the turn ends.", "type": "number" }, "silence_ms": { "description": "Silence, in milliseconds, before a turn is evaluated.", "type": "integer" }, "stop_s": { "description": "Silence, in seconds, that ends the turn whatever the probability.", "type": "number" }, "reeval_ms": { "description": "Interval, in milliseconds, between two evaluations of the same silence.", "type": "integer" }, "window_s": { "description": "Audio, in seconds, the evaluation reads before the silence.", "type": "number" }, "speech_dbfs": { "description": "Level, in dBFS, under which audio counts as silence.", "type": "number" } }, "required": [ "threshold", "silence_ms", "stop_s", "reeval_ms", "window_s", "speech_dbfs" ], "title": "EndOfTurnDefaults", "type": "object" }, "EndOfTurnMessage": { "additionalProperties": false, "description": "The speaker finished their turn (`end_of_turn`): a voice agent may answer.", "properties": { "type": { "const": "end_of_turn", "type": "string" }, "session_id": { "type": "string" }, "data": { "$ref": "#/components/schemas/EndOfTurnData" } }, "required": [ "type", "session_id", "data" ], "title": "EndOfTurnMessage", "type": "object" }, "EndRecordingData": { "additionalProperties": false, "properties": { "recording_duration": { "description": "Audio received, in seconds.", "type": "number" } }, "required": [ "recording_duration" ], "title": "EndRecordingData", "type": "object" }, "EndRecordingMessage": { "additionalProperties": false, "description": "No more audio is accepted (`receive_lifecycle_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "end_recording", "type": "string" }, "data": { "$ref": "#/components/schemas/EndRecordingData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "EndRecordingMessage", "type": "object" }, "EndSessionMessage": { "additionalProperties": false, "description": "The last message: the server closes the WebSocket after it (`receive_lifecycle_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "end_session", "type": "string" } }, "required": [ "session_id", "created_at", "type" ], "title": "EndSessionMessage", "type": "object" }, "Entity": { "additionalProperties": true, "description": "A named entity or a piece of personal data found in an utterance.", "properties": { "label": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Entity type, for example `name`, `phone_number`, `location_city`." }, "id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "The entity's number in the session, per type: the same person is always the same number." }, "action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "`ner`: tagged; otherwise how the personal data was redacted." }, "score": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "description": "Confidence, from 0 to 1." }, "text": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The entity as heard (never sent for masked personal data unless `pii.return_entities`)." }, "start": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "Offset of the entity's element in `text`, in characters." }, "end": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "End offset of the entity's element in `text`, in characters." } }, "title": "Entity", "type": "object" }, "EntitySelection": { "title": "EntitySelection", "type": "object", "additionalProperties": false, "properties": { "entities": { "anyOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } }, { "type": "object", "properties": { "enable": { "type": "array", "items": { "type": "string" } }, "disable": { "type": "array", "items": { "type": "string" } } } } ], "description": "Which types: a preset (`pii`, `pci`, `phi`, `contact`, `financial`, `name`, `location`, `date`…), a list of types and presets, or `{\"enable\": [...], \"disable\": [...]}`." }, "threshold": { "type": "number", "minimum": 0, "maximum": 1, "default": 0.5, "description": "Confidence, from 0 to 1, under which an entity is ignored." } } }, "ErrorMessage": { "additionalProperties": true, "description": "Something failed during the session (`receive_errors`).", "properties": { "type": { "const": "error", "type": "string" }, "session_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "error": { "$ref": "#/components/schemas/JsonValue", "default": null, "description": "What failed." } }, "required": [ "type" ], "title": "ErrorMessage", "type": "object" }, "ErrorResponse": { "additionalProperties": false, "description": "Every error of the HTTP API.", "properties": { "statusCode": { "description": "HTTP status code of the error.", "examples": [ 400 ], "type": "integer" }, "timestamp": { "description": "When the error occurred (ISO 8601, UTC).", "examples": [ "2026-10-12T09:04:17.210Z" ], "type": "string" }, "path": { "description": "Path of the endpoint that answered.", "examples": [ "/v2/live" ], "type": "string" }, "message": { "description": "What went wrong.", "examples": [ "Invalid parameter(s). See validation_errors for more details." ], "type": "string" }, "request_id": { "description": "Identifier to quote to support.", "examples": [ "G-1a2b3c4d" ], "type": "string" }, "validation_errors": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "One message per invalid field (`400` only): the field's path, then the rule it breaks.", "examples": [ [ "sample_rate Input should be 8000, 16000, 32000, 44100 or 48000" ] ] }, "error": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "A machine-readable reason, on some refusals (for example `ip_not_allowed`, `api_key_scope_denied`)." } }, "required": [ "statusCode", "timestamp", "path", "message", "request_id" ], "title": "ErrorResponse", "type": "object" }, "LiveInitRequest": { "additionalProperties": false, "properties": { "encoding": { "default": "wav/pcm", "enum": [ "wav/pcm", "wav/alaw", "wav/ulaw" ], "type": "string", "description": "Encoding of the audio you send." }, "bit_depth": { "default": 16, "enum": [ 8, 16, 24, 32 ], "type": "integer", "description": "Bit depth of the audio. `wav/alaw` and `wav/ulaw` are 8-bit." }, "sample_rate": { "default": 16000, "enum": [ 8000, 16000, 32000, 44100, 48000 ], "type": "integer", "description": "Sample rate of the audio, in Hz." }, "channels": { "default": 1, "maximum": 8, "minimum": 1, "type": "integer", "description": "Number of interleaved audio channels. Each channel is transcribed on its own: put each speaker of a call on their own channel to know who said what without diarization." }, "custom_metadata": { "additionalProperties": { "$ref": "#/components/schemas/JsonValue" }, "type": "object", "description": "Any JSON object, kept with the session: returned by `GET /v2/live/{id}`, sent to your callback, and a filter of `GET /v2/live`." }, "model": { "type": "string", "enum": [ "solaria-3", "solaria-1", "trantoria-1", "solaria-3-fast", "solaria-3-medium", "solaria-3-balanced", "solaria-3-precise", "solaria-1-fast", "solaria-1-medium", "solaria-1-balanced", "solaria-1-precise", "trantoria-1-fast", "trantoria-1-medium", "trantoria-1-balanced", "trantoria-1-precise", "fast", "medium", "balanced", "precise" ], "examples": [ "solaria-3" ], "description": "The model, by name, optionally with a latency profile (`solaria-3-fast`), or a latency profile alone (`fast`). Omitted: the default model of your account." }, "endpointing": { "default": 0.64, "maximum": 10, "minimum": 0.01, "type": "number", "description": "Silence, in seconds, that ends an utterance and produces its final transcript. Short values give faster finals and may cut sentences at hesitations." }, "maximum_duration_without_endpointing": { "maximum": 60, "minimum": 5, "type": "number", "description": "Longest utterance, in seconds: a final is forced after this much speech without a pause. Omitted: no limit." }, "language_config": { "$ref": "#/components/schemas/LanguageConfig", "description": "The languages to expect." }, "realtime_processing": { "$ref": "#/components/schemas/RealtimeProcessing", "description": "Processing applied to each final transcript, during the session." }, "messages_config": { "$ref": "#/components/schemas/MessagesConfig", "description": "The messages sent on the WebSocket." }, "callback": { "default": false, "type": "boolean", "description": "Also send the session's messages to `callback_config.url`, by HTTP POST." }, "callback_config": { "anyOf": [ { "$ref": "#/components/schemas/CallbackConfig" }, { "type": "null" } ], "default": null, "description": "Where and which messages the callback receives. Required with `callback`." }, "profile": { "anyOf": [ { "enum": [ "fast", "medium", "balanced", "precise" ], "type": "string" }, { "type": "null" } ], "default": null, "description": "Latency profile: `fast` gives the earliest transcripts, `precise` the most accurate ones. The same as a profile in `model`." }, "diarization": { "default": false, "type": "boolean", "description": "Speaker labels on single-channel audio: each utterance and word gets a `speaker` number." }, "diarization_config": { "$ref": "#/components/schemas/DiarizationConfig", "description": "Diarization options." }, "punctuation": { "default": true, "type": "boolean", "description": "Punctuation and casing of the transcripts. On unless `false`." }, "end_of_turn": { "anyOf": [ { "type": "boolean" }, { "$ref": "#/components/schemas/EndOfTurnConfig" } ], "default": false, "description": "End-of-turn detection for voice agents: an `end_of_turn` message when the speaker has finished their turn, judged from how they speak and not from silence alone. `true` uses the defaults (`GET /v2/live/defaults`), an object overrides some of them. Off when omitted." }, "numerals": { "anyOf": [ { "type": "boolean" }, { "$ref": "#/components/schemas/NumeralsConfig" } ], "default": false, "description": "Spoken numbers, amounts and clock times written with digits in the final transcripts (\"one thousand three hundred fifty five dollars\" becomes \"$1,355\", \"at nine fifteen\" \"at 9:15\"); `text_raw` keeps the words. Where the turn router runs (the default; not with `turn_router: false`), it guides them: phone numbers are also written in their country's format (\"06 12 34 56 78\") and dates the language's way (\"March 12, 2026\"). `true` uses the countries of the language spoken, an object sets the country." }, "named_entity_recognition": { "anyOf": [ { "type": "boolean" }, { "$ref": "#/components/schemas/EntitySelection" } ], "default": false, "description": "Named entities (people, places, organizations, dates, amounts…) tagged in the final transcripts, and a `named_entity_recognition` message after each final. `true` tags every type." }, "pii": { "anyOf": [ { "type": "boolean" }, { "$ref": "#/components/schemas/PiiConfig" } ], "default": false, "description": "Personal data (names, phone numbers, emails, card numbers…) redacted in the final transcripts, and a `pii` message after each final. With redaction on, no partial transcript is sent." }, "turn_router": { "anyOf": [ { "type": "boolean" }, { "$ref": "#/components/schemas/TurnRouterConfig" } ], "description": "The number hold: an utterance stays open while a number, an amount or an address is still being dictated, so it is not cut at each pause. On by default where the model supports it; `false` turns it off." } }, "title": "InitBody", "type": "object" }, "InitResponse": { "additionalProperties": false, "description": "A live session, created: connect to `url` to stream its audio.", "properties": { "id": { "description": "Identifier of the session (a time-ordered UUID).", "examples": [ "0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b" ], "type": "string" }, "created_at": { "description": "Creation date (ISO 8601, UTC).", "examples": [ "2026-10-12T09:04:17.210Z" ], "type": "string" }, "url": { "description": "WebSocket URL to stream the audio to. It carries a single-use token: connect within 60 seconds. Reconnecting to the same URL after a dropped connection resumes the session.", "examples": [ "wss://eu1.api.gladia.io/v2/live?token=eyJhbGciOi..." ], "type": "string" } }, "required": [ "id", "created_at", "url" ], "title": "InitResponse", "type": "object" }, "JsonValue": {}, "LanguageConfig": { "additionalProperties": false, "properties": { "languages": { "items": { "type": "string" }, "type": "array", "description": "The languages that may be spoken (ISO 639-1 codes). Empty: the language is detected. One or more codes: the session is transcribed in the first one, unless `code_switching`." }, "code_switching": { "default": false, "type": "boolean", "description": "Detect the language as the conversation goes, among `languages` when given: for speakers who switch languages." } }, "title": "LanguageConfig", "type": "object" }, "LiveCapabilities": { "additionalProperties": false, "description": "What `POST /v2/live` accepts for the calling key right now.", "properties": { "models": { "description": "The models with an inference endpoint open to this key; empty when none is.", "items": { "$ref": "#/components/schemas/ModelCapabilities" }, "type": "array" } }, "required": [ "models" ], "title": "LiveCapabilities", "type": "object" }, "LiveFile": { "additionalProperties": false, "properties": { "id": { "description": "Identifier of the session.", "type": "string" }, "filename": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Name of the recording, `null` when the audio was not recorded." }, "source": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "Download URL of the recording (`GET /v2/live/{id}/file`), `null` when not recorded." }, "audio_duration": { "description": "Audio received, in seconds.", "type": "number" }, "number_of_channels": { "type": "integer" } }, "required": [ "id", "filename", "source", "audio_duration", "number_of_channels" ], "title": "LiveFile", "type": "object" }, "LiveResult": { "additionalProperties": false, "properties": { "metadata": { "$ref": "#/components/schemas/TranscriptionMetadata" }, "transcription": { "$ref": "#/components/schemas/Transcription" }, "translation": { "anyOf": [ { "$ref": "#/components/schemas/TranslationResult" }, { "type": "null" } ], "default": null, "description": "With `realtime_processing.translation`." }, "messages": { "description": "The final transcript messages, as sent on the WebSocket.", "items": { "$ref": "#/components/schemas/JsonValue" }, "type": "array" } }, "required": [ "metadata", "transcription", "messages" ], "title": "LiveResult", "type": "object" }, "LiveSession": { "additionalProperties": false, "description": "A live session: its status, its options and, once done, its result.", "properties": { "id": { "description": "Identifier of the session.", "examples": [ "0199d7a2-5c3e-7b41-9f0a-3c2d1e4f5a6b" ], "type": "string" }, "request_id": { "description": "Identifier to quote to support.", "examples": [ "G-0199d7a2" ], "type": "string" }, "version": { "const": 2, "default": 2, "type": "integer" }, "status": { "description": "`queued`: created, no WebSocket yet; `processing`: streaming (or dropped and still resumable); `done`: ended, the result is there; `error`: the session failed.", "enum": [ "queued", "processing", "done", "error" ], "type": "string" }, "created_at": { "description": "Creation date (ISO 8601, UTC).", "type": "string" }, "completed_at": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "End date, once `done` or `error`." }, "custom_metadata": { "additionalProperties": { "$ref": "#/components/schemas/JsonValue" }, "description": "The init body's `custom_metadata`.", "type": "object" }, "error_code": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "`500` when the session failed, else `null`." }, "kind": { "const": "live", "default": "live", "type": "string" }, "file": { "anyOf": [ { "$ref": "#/components/schemas/LiveFile" }, { "type": "null" } ], "description": "The session's audio, once it ended." }, "request_params": { "anyOf": [ { "additionalProperties": { "$ref": "#/components/schemas/JsonValue" }, "type": "object" }, { "type": "null" } ], "description": "The session's options, as validated." }, "result": { "anyOf": [ { "$ref": "#/components/schemas/LiveResult" }, { "type": "null" } ], "description": "The transcript, once `done`." } }, "required": [ "id", "request_id", "status", "created_at", "completed_at", "custom_metadata", "error_code", "file", "request_params", "result" ], "title": "LiveSession", "type": "object" }, "LiveSessionList": { "additionalProperties": false, "properties": { "first": { "description": "URL of the first page.", "type": "string" }, "current": { "description": "URL of this page.", "type": "string" }, "next": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "description": "URL of the next page (it carries a `cursor`), `null` on the last page." }, "items": { "description": "The sessions, newest first.", "items": { "$ref": "#/components/schemas/LiveSession" }, "type": "array" } }, "required": [ "first", "current", "next", "items" ], "title": "LiveSessionList", "type": "object" }, "MessagesConfig": { "additionalProperties": false, "properties": { "receive_partial_transcripts": { "default": false, "type": "boolean", "description": "Partial transcripts, updated while the utterance is spoken." }, "receive_final_transcripts": { "default": true, "type": "boolean", "description": "The final transcript of each utterance." }, "receive_speech_events": { "default": true, "type": "boolean", "description": "`speech_start` and `speech_end`." }, "receive_pre_processing_events": { "default": true, "type": "boolean", "description": "Pre-processing messages." }, "receive_realtime_processing_events": { "default": true, "type": "boolean", "description": "Messages of the realtime processing: `translation`, `named_entity_recognition`, `sentiment_analysis`." }, "receive_post_processing_events": { "default": true, "type": "boolean", "description": "`post_transcript` and `post_final_transcript`, at the end." }, "receive_acknowledgments": { "default": true, "type": "boolean", "description": "`audio_chunk` and `stop_recording` acknowledgments." }, "receive_errors": { "default": true, "type": "boolean", "description": "`error` messages." }, "receive_lifecycle_events": { "default": false, "type": "boolean", "description": "`start_recording`, `end_recording` and `end_session`." } }, "title": "MessagesConfig", "type": "object" }, "ModelCapabilities": { "additionalProperties": false, "description": "A model an inference endpoint takes for the calling key, and its add-ons.", "properties": { "model": { "description": "The model's code name, as the init body's `model` takes it.", "examples": [ "solaria-3" ], "type": "string" }, "addons": { "description": "The add-ons a session on this model may ask for, by the init body's option name.", "examples": [ [ "named_entity_recognition", "pii", "translation" ] ], "items": { "type": "string" }, "type": "array" } }, "required": [ "model", "addons" ], "title": "ModelCapabilities", "type": "object" }, "NamedEntity": { "additionalProperties": false, "properties": { "entity_type": { "description": "The entity's type, for example `name`.", "type": "string" }, "text": { "description": "The entity as heard.", "type": "string" }, "start": { "description": "Start, in seconds.", "type": "number" }, "end": { "description": "End, in seconds.", "type": "number" }, "id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "The entity's number in the session: the same person is always the same number." }, "score": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "description": "Confidence, from 0 to 1." }, "char_start": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "Offset of the entity's element in the final's `text`." }, "char_end": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "End offset of the entity's element in the final's `text`." } }, "required": [ "entity_type", "text", "start", "end" ], "title": "NamedEntity", "type": "object" }, "NamedEntityData": { "additionalProperties": false, "properties": { "utterance_id": { "type": "string" }, "utterance": { "$ref": "#/components/schemas/Utterance" }, "results": { "items": { "$ref": "#/components/schemas/NamedEntity" }, "type": "array" } }, "required": [ "utterance_id", "utterance", "results" ], "title": "NamedEntityData", "type": "object" }, "NamedEntityRecognitionMessage": { "additionalProperties": false, "description": "The entities of a final, right after it (`receive_realtime_processing_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "named_entity_recognition", "type": "string" }, "error": { "anyOf": [ { "$ref": "#/components/schemas/AddonError" }, { "type": "null" } ], "default": null }, "data": { "$ref": "#/components/schemas/NamedEntityData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "NamedEntityRecognitionMessage", "type": "object" }, "NumeralsConfig": { "additionalProperties": false, "description": "`numerals` options: the country whose format the phone numbers and dates of the final\ntranscripts are written in.", "properties": { "region": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The country whose phone numbers and dates the transcripts are written in: an ISO 3166-1 alpha-2 code in capitals (`CH`, `CA`). Omitted: the countries where the language is spoken." } }, "title": "NumeralsConfig", "type": "object" }, "PiiConfig": { "title": "PiiConfig", "type": "object", "additionalProperties": false, "properties": { "entities": { "anyOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } }, { "type": "object", "properties": { "enable": { "type": "array", "items": { "type": "string" } }, "disable": { "type": "array", "items": { "type": "string" } } } } ], "default": "pii", "description": "Which types to redact: a preset (`pii`, the default; `pci`, `phi`, `contact`, `financial`…), a list of types and presets, or `{\"enable\": [...], \"disable\": [...]}`." }, "mode": { "type": "string", "enum": [ "marker", "mask", "tag" ], "default": "marker", "description": "`marker` replaces the data with an element (``), `mask` with mask characters inside the element, `tag` keeps the text inside the element." }, "threshold": { "type": "number", "minimum": 0, "maximum": 1, "default": 0.5, "description": "Confidence, from 0 to 1, under which a span is not redacted." }, "mask_character": { "type": "string", "default": "*", "minLength": 1, "maxLength": 1, "description": "The character of `mask` mode." }, "coreference": { "type": "string", "enum": [ "heuristics", "exact", "off" ], "default": "heuristics", "description": "How mentions of the same entity get the same `id`: `heuristics` (the default), `exact` (same text only) or `off`." }, "return_entities": { "type": "boolean", "default": false, "description": "Also return the redacted text in the `pii` message (`text`)." } } }, "PiiData": { "additionalProperties": false, "properties": { "utterance_id": { "type": "string" }, "utterance": { "$ref": "#/components/schemas/Utterance" }, "results": { "items": { "$ref": "#/components/schemas/PiiEntity" }, "type": "array" } }, "required": [ "utterance_id", "utterance", "results" ], "title": "PiiData", "type": "object" }, "PiiEntity": { "additionalProperties": false, "properties": { "entity_type": { "description": "The kind of personal data, for example `phone_number`.", "type": "string" }, "id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "Its number in the session." }, "action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "What was done: masked or tagged." }, "char_start": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "char_end": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "text": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The data as heard, only with `pii.return_entities`." } }, "required": [ "entity_type" ], "title": "PiiEntity", "type": "object" }, "PiiMessage": { "additionalProperties": false, "description": "The personal data redacted in a final, right after it (with `pii`; on the WebSocket\nonly).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "pii", "type": "string" }, "error": { "anyOf": [ { "$ref": "#/components/schemas/AddonError" }, { "type": "null" } ], "default": null }, "data": { "$ref": "#/components/schemas/PiiData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "PiiMessage", "type": "object" }, "PostFinalData": { "additionalProperties": false, "properties": { "metadata": { "$ref": "#/components/schemas/TranscriptionMetadata" }, "transcription": { "$ref": "#/components/schemas/Transcription" }, "translation": { "anyOf": [ { "$ref": "#/components/schemas/TranslationResult" }, { "type": "null" } ], "default": null } }, "required": [ "metadata", "transcription" ], "title": "PostFinalData", "type": "object" }, "PostFinalTranscriptMessage": { "additionalProperties": false, "description": "The session's result, the same as `GET /v2/live/{id}`'s\n(`receive_post_processing_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "post_final_transcript", "type": "string" }, "data": { "$ref": "#/components/schemas/PostFinalData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "PostFinalTranscriptMessage", "type": "object" }, "PostTranscriptMessage": { "additionalProperties": false, "description": "The whole session's transcript, after `end_recording`\n(`receive_post_processing_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "post_transcript", "type": "string" }, "data": { "$ref": "#/components/schemas/Transcription" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "PostTranscriptMessage", "type": "object" }, "RealtimeProcessing": { "additionalProperties": false, "properties": { "custom_vocabulary": { "default": false, "type": "boolean", "description": "Bias the transcription toward the words of `custom_vocabulary_config`." }, "custom_vocabulary_config": { "anyOf": [ { "$ref": "#/components/schemas/CustomVocabularyConfig" }, { "type": "null" } ], "default": null, "description": "The words to favour. Required with `custom_vocabulary`." }, "custom_spelling": { "default": false, "type": "boolean", "description": "Rewrite words as `custom_spelling_config` says." }, "custom_spelling_config": { "anyOf": [ { "$ref": "#/components/schemas/CustomSpellingConfig" }, { "type": "null" } ], "default": null, "description": "The spellings to apply. Required with `custom_spelling`." }, "translation": { "default": false, "type": "boolean", "description": "Translate each final transcript into the target languages." }, "translation_config": { "anyOf": [ { "$ref": "#/components/schemas/TranslationConfig" }, { "type": "null" } ], "default": null, "description": "The target languages. Required with `translation`." }, "named_entity_recognition": { "default": false, "type": "boolean", "description": "The same as the top-level `named_entity_recognition: true`." }, "sentiment_analysis": { "default": false, "type": "boolean", "description": "The sentiment (positive, neutral, negative) and emotion of each final, in a `sentiment_analysis` message after it." } }, "title": "RealtimeProcessing", "type": "object" }, "Sentiment": { "additionalProperties": false, "properties": { "sentiment": { "enum": [ "positive", "neutral", "negative" ], "type": "string" }, "emotion": { "description": "The dominant emotion, for example `joy`; empty when none.", "type": "string" }, "text": { "type": "string" }, "start": { "type": "number" }, "end": { "type": "number" }, "channel": { "type": "integer" } }, "required": [ "sentiment", "emotion", "text", "start", "end", "channel" ], "title": "Sentiment", "type": "object" }, "SentimentAnalysisMessage": { "additionalProperties": false, "description": "The sentiment of a final, right after it (`receive_realtime_processing_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "sentiment_analysis", "type": "string" }, "error": { "anyOf": [ { "$ref": "#/components/schemas/AddonError" }, { "type": "null" } ], "default": null }, "data": { "$ref": "#/components/schemas/SentimentData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "SentimentAnalysisMessage", "type": "object" }, "SentimentData": { "additionalProperties": false, "properties": { "utterance_id": { "type": "string" }, "utterance": { "$ref": "#/components/schemas/Utterance" }, "results": { "items": { "$ref": "#/components/schemas/Sentiment" }, "type": "array" } }, "required": [ "utterance_id", "utterance", "results" ], "title": "SentimentData", "type": "object" }, "SessionDefaults": { "additionalProperties": false, "description": "What a session gets for each option its init body omits.", "properties": { "endpointing": { "description": "Silence, in seconds, that ends an utterance.", "examples": [ 0.64 ], "type": "number" }, "maximum_duration_without_endpointing": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "description": "Longest utterance, in seconds, before a final is forced; `null`: no limit." }, "end_of_turn": { "anyOf": [ { "$ref": "#/components/schemas/EndOfTurnDefaults" }, { "type": "null" } ], "description": "The end-of-turn options a session starts from." }, "turn_router": { "anyOf": [ { "$ref": "#/components/schemas/TurnHoldDefaults" }, { "type": "null" } ], "description": "The number hold a session gets when the model serving it supports it." } }, "required": [ "endpointing", "maximum_duration_without_endpointing", "end_of_turn", "turn_router" ], "title": "SessionDefaults", "type": "object" }, "SpeechEndMessage": { "additionalProperties": false, "description": "Speech ended on a channel (`receive_speech_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "speech_end", "type": "string" }, "data": { "$ref": "#/components/schemas/SpeechEventData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "SpeechEndMessage", "type": "object" }, "SpeechEventData": { "additionalProperties": false, "properties": { "time": { "description": "When speech started or ended, in seconds.", "type": "number" }, "channel": { "type": "integer" } }, "required": [ "time", "channel" ], "title": "SpeechEventData", "type": "object" }, "SpeechStartMessage": { "additionalProperties": false, "description": "Speech started on a channel (`receive_speech_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "speech_start", "type": "string" }, "data": { "$ref": "#/components/schemas/SpeechEventData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "SpeechStartMessage", "type": "object" }, "StartRecordingMessage": { "additionalProperties": false, "description": "The session is ready: audio may be sent (`messages_config.receive_lifecycle_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "start_recording", "type": "string" } }, "required": [ "session_id", "created_at", "type" ], "title": "StartRecordingMessage", "type": "object" }, "StopRecordingAckData": { "additionalProperties": false, "properties": { "recording_duration": { "description": "Audio received, in seconds.", "type": "number" }, "recording_left_to_process": { "description": "Audio, in seconds, still being transcribed.", "type": "number" } }, "required": [ "recording_duration", "recording_left_to_process" ], "title": "StopRecordingAckData", "type": "object" }, "StopRecordingAckMessage": { "additionalProperties": false, "description": "The answer to `stop_recording` (`receive_acknowledgments`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "stop_recording", "type": "string" }, "acknowledged": { "type": "boolean" }, "error": { "$ref": "#/components/schemas/JsonValue", "default": null }, "data": { "$ref": "#/components/schemas/StopRecordingAckData" } }, "required": [ "session_id", "created_at", "type", "acknowledged", "data" ], "title": "StopRecordingAckMessage", "type": "object" }, "StopRecordingAction": { "additionalProperties": false, "description": "No more audio: the server sends the last finals, the post-processing results, then ends\nthe session.", "properties": { "type": { "const": "stop_recording", "type": "string" } }, "required": [ "type" ], "title": "StopRecordingAction", "type": "object" }, "TranscriptData": { "additionalProperties": false, "properties": { "id": { "description": "Identifier of the utterance: `_`, stable for the whole session.", "examples": [ "00_00000003" ], "type": "string" }, "is_final": { "description": "`false`: a partial transcript, replaced by the next one; `true`: the final transcript of the utterance.", "type": "boolean" }, "utterance": { "$ref": "#/components/schemas/Utterance" } }, "required": [ "id", "is_final", "utterance" ], "title": "TranscriptData", "type": "object" }, "TranscriptMessage": { "additionalProperties": false, "description": "A partial (`receive_partial_transcripts`) or final (`receive_final_transcripts`)\ntranscript.", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "transcript", "type": "string" }, "data": { "$ref": "#/components/schemas/TranscriptData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "TranscriptMessage", "type": "object" }, "Transcription": { "additionalProperties": false, "properties": { "languages": { "description": "Languages heard, in order of appearance.", "items": { "type": "string" }, "type": "array" }, "utterances": { "description": "Every final utterance, by start time.", "items": { "$ref": "#/components/schemas/Utterance" }, "type": "array" }, "full_transcript": { "description": "The final utterances' text, joined.", "type": "string" } }, "required": [ "languages", "utterances", "full_transcript" ], "title": "Transcription", "type": "object" }, "TranscriptionMetadata": { "additionalProperties": false, "properties": { "audio_duration": { "description": "Audio received, in seconds.", "type": "number" }, "billing_time": { "description": "Billed duration, in seconds.", "type": "number" }, "number_of_distinct_channels": { "description": "Number of audio channels.", "type": "integer" }, "transcription_time": { "description": "How long the session ran, in seconds.", "type": "number" } }, "required": [ "audio_duration", "billing_time", "number_of_distinct_channels", "transcription_time" ], "title": "TranscriptionMetadata", "type": "object" }, "TranslationConfig": { "additionalProperties": false, "properties": { "target_languages": { "items": { "type": "string" }, "minItems": 1, "type": "array", "description": "The languages to translate into (ISO 639-1 codes)." } }, "required": [ "target_languages" ], "title": "TranslationConfig", "type": "object" }, "TranslationData": { "additionalProperties": false, "properties": { "utterance_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ] }, "utterance": { "anyOf": [ { "$ref": "#/components/schemas/Utterance" }, { "additionalProperties": { "$ref": "#/components/schemas/JsonValue" }, "type": "object" } ] }, "original_language": { "anyOf": [ { "type": "string" }, { "type": "null" } ] }, "target_language": { "anyOf": [ { "type": "string" }, { "type": "null" } ] }, "translated_utterance": { "anyOf": [ { "$ref": "#/components/schemas/Utterance" }, { "type": "null" } ], "description": "`null` when the translation failed (see `error`)." } }, "required": [ "utterance_id", "utterance", "original_language", "target_language", "translated_utterance" ], "title": "TranslationData", "type": "object" }, "TranslationMessage": { "additionalProperties": false, "description": "One final translated into one target language (`receive_realtime_processing_events`).", "properties": { "session_id": { "description": "Identifier of the session.", "type": "string" }, "created_at": { "description": "When the message was sent (ISO 8601, UTC).", "type": "string" }, "type": { "const": "translation", "type": "string" }, "error": { "$ref": "#/components/schemas/JsonValue", "default": null }, "data": { "$ref": "#/components/schemas/TranslationData" } }, "required": [ "session_id", "created_at", "type", "data" ], "title": "TranslationMessage", "type": "object" }, "TranslationResult": { "additionalProperties": false, "properties": { "success": { "type": "boolean" }, "is_empty": { "description": "`true` when nothing was translated.", "type": "boolean" }, "exec_time": { "type": "number" }, "error": { "$ref": "#/components/schemas/JsonValue", "default": null }, "results": { "description": "One result per target language.", "items": { "$ref": "#/components/schemas/TranslationResultItem" }, "type": "array" } }, "required": [ "success", "is_empty", "exec_time", "results" ], "title": "TranslationResult", "type": "object" }, "TranslationResultItem": { "additionalProperties": false, "properties": { "error": { "$ref": "#/components/schemas/JsonValue", "default": null, "description": "Always `null`." }, "languages": { "description": "The target language of this result.", "items": { "type": "string" }, "type": "array" }, "full_transcript": { "description": "The translated text, joined.", "type": "string" }, "utterances": { "description": "The translated utterances, one per final.", "items": { "$ref": "#/components/schemas/Utterance" }, "type": "array" }, "sentences": { "description": "Always empty.", "items": { "$ref": "#/components/schemas/JsonValue" }, "type": "array" }, "subtitles": { "description": "Always empty.", "items": { "$ref": "#/components/schemas/JsonValue" }, "type": "array" } }, "required": [ "languages", "full_transcript", "utterances", "sentences", "subtitles" ], "title": "TranslationResultItem", "type": "object" }, "TurnHoldDefaults": { "additionalProperties": false, "properties": { "hold": { "description": "An utterance stays open while a number, an amount or an address is still being dictated.", "type": "boolean" }, "emit": { "description": "Turn verdicts sent as messages.", "type": "boolean" }, "route_numerals": { "description": "Number words routed through the hold.", "type": "boolean" } }, "required": [ "hold", "emit", "route_numerals" ], "title": "TurnHoldDefaults", "type": "object" }, "TurnRouterConfig": { "title": "TurnRouterConfig", "type": "object", "additionalProperties": false, "properties": { "hold": { "type": "boolean", "description": "The number hold." } } }, "Utterance": { "additionalProperties": true, "description": "A piece of speech between two pauses, on one channel.", "properties": { "text": { "description": "The transcript. With named entity recognition or PII redaction on, it carries their inline elements (`…`, ``).", "examples": [ "Hello, how can I help you?" ], "type": "string" }, "start": { "description": "Start, in seconds from the start of the audio.", "type": "number" }, "end": { "description": "End, in seconds from the start of the audio.", "type": "number" }, "language": { "description": "Language spoken (ISO 639-1).", "examples": [ "en" ], "type": "string" }, "confidence": { "description": "Confidence, from 0 to 1.", "type": "number" }, "channel": { "description": "Audio channel the utterance was heard on, from 0.", "type": "integer" }, "speaker": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "Speaker number, with `diarization`." }, "words": { "description": "The words with their timestamps.", "items": { "$ref": "#/components/schemas/Word" }, "type": "array" }, "text_raw": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The transcript without inline elements (with named entity recognition; never with PII redaction)." }, "entities": { "anyOf": [ { "items": { "$ref": "#/components/schemas/Entity" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "The entities of the utterance, with named entity recognition or PII redaction." }, "forced": { "anyOf": [ { "const": "max_duration", "type": "string" }, { "type": "null" } ], "default": null, "description": "Set when the utterance was closed by `maximum_duration_without_endpointing` rather than by a pause." } }, "required": [ "text", "start", "end", "language", "confidence", "channel", "words" ], "title": "Utterance", "type": "object" }, "VocabularyItem": { "additionalProperties": false, "properties": { "value": { "type": "string", "description": "The word or phrase." }, "intensity": { "anyOf": [ { "maximum": 1, "minimum": 0, "type": "number" }, { "type": "null" } ], "default": null, "description": "How strongly it is favoured, from 0 to 1." }, "pronunciations": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "Other ways it may be pronounced, written as they sound." } }, "required": [ "value" ], "title": "VocabularyItem", "type": "object" }, "Word": { "additionalProperties": false, "properties": { "word": { "description": "The word, with its leading space when it follows another.", "examples": [ " hello" ], "type": "string" }, "start": { "description": "Start of the word, in seconds from the start of the audio.", "type": "number" }, "end": { "description": "End of the word, in seconds from the start of the audio.", "type": "number" }, "confidence": { "description": "Confidence, from 0 to 1.", "type": "number" }, "speaker": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null, "description": "Speaker of the word, with `diarization`." } }, "required": [ "word", "start", "end", "confidence" ], "title": "Word", "type": "object" } } } }