--- updatedAt: 2026-07-21T08:40:48.000Z agentTools: projectIndex: https://developers.intandem.tech/llms.txt --- # Create an AudioTranscription ## Overview Transcribe audio files using multiple providers (OpenAI Whisper, OpenAI GPT-4o Transcribe, Google Chirp). Supports file upload via multipart form data. ### Supported Models | Provider | Models | |----------|--------| | OpenAI | `openai/whisper-1`, `openai/gpt-4o-transcribe` | | Google | `google/chirp-2` | ### Async Mode Set `async: true` to queue the transcription and receive a run UID. Poll `GET /v3/ai/transcription_runs/{uid}` for the result. Recommended for long audio files or diarization. **Available for Staff tokens** # OpenAPI definition ```json { "openapi": "3.1.0", "info": { "title": "Ai", "description": "Unified OpenAPI specification for ai domain", "version": "3.0", "x-generated": { "sourceFiles": [ "recommendations.json", "business_rules.json", "business_ai_settings.json", "bizai.json", "ai_smart_reply.json", "generic_ai.json", "staff_ai_settings.json", "ai_generation_feedback.json" ], "pathNormalizations": [], "pathConflicts": [], "componentConflicts": [ { "type": "schema", "name": "ErrorResponse", "resolution": "Renamed to ErrorResponse_business_rules", "files": [ "merged", "business_rules.json" ] }, { "type": "schema", "name": "ErrorResponse", "resolution": "Renamed to ErrorResponse_business_ai_settings", "files": [ "merged", "business_ai_settings.json" ] }, { "type": "schema", "name": "Response", "resolution": "Renamed to Response_ai_smart_reply", "files": [ "merged", "ai_smart_reply.json" ] }, { "type": "schema", "name": "ErrorResponse", "resolution": "Renamed to ErrorResponse_staff_ai_settings", "files": [ "merged", "staff_ai_settings.json" ] } ], "totalPaths": 20, "totalComponents": 33 } }, "servers": [ { "url": "https://api.vcita.biz", "description": "Unified API Gateway server" } ], "paths": { "/v3/ai/audio_transcriptions": { "post": { "tags": [ "AI Audio Transcriptions" ], "summary": "Create an AudioTranscription", "description": "## Overview\nTranscribe audio files using multiple providers (OpenAI Whisper, OpenAI GPT-4o Transcribe, Google Chirp). Supports file upload via multipart form data.\n\n### Supported Models\n| Provider | Models |\n|----------|--------|\n| OpenAI | `openai/whisper-1`, `openai/gpt-4o-transcribe` |\n| Google | `google/chirp-2` |\n\n### Async Mode\nSet `async: true` to queue the transcription and receive a run UID. Poll `GET /v3/ai/transcription_runs/{uid}` for the result. Recommended for long audio files or diarization.\n\n**Available for Staff tokens**", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "type": "object", "properties": { "file": { "type": "string", "format": "binary", "description": "Audio file to transcribe (max 25MB). Supported formats: mp3, mp4, m4a, wav, webm, flac, ogg." }, "model": { "type": "string", "description": "Model identifier in provider/model format (e.g., \"openai/gpt-4o-transcribe\", \"openai/whisper-1\", \"google/chirp-2\").", "example": "openai/gpt-4o-transcribe" }, "language": { "type": "string", "description": "ISO-639-1 language code for the audio content (e.g., \"en\" for English, \"es\" for Spanish, \"he\" for Hebrew). When omitted, the provider will auto-detect the language." }, "prompt": { "type": "string", "description": "Optional guiding prompt to improve transcription accuracy. Useful for providing context, domain-specific terminology, or correcting recurring misrecognitions." }, "response_format": { "type": "string", "enum": [ "json", "text", "srt", "verbose_json", "vtt" ], "description": "Desired response format. 'json' returns a simple JSON with text, 'text' returns plain text, 'srt' returns SubRip subtitle format, 'verbose_json' returns detailed JSON with word-level timestamps, 'vtt' returns WebVTT subtitle format. Defaults to 'json'." }, "temperature": { "type": "number", "minimum": 0, "maximum": 1, "description": "Sampling temperature between 0 and 1. Higher values make the output more random, while lower values make it more deterministic. Defaults to 0." }, "async": { "type": "boolean", "description": "Process the request asynchronously. Returns a run UID immediately that can be polled via GET /v3/ai/transcription_runs/{uid}. Recommended for long audio files or when diarization is needed.", "default": false } }, "required": [ "file", "model" ] } } } }, "responses": { "200": { "description": "Successful transcription.", "content": { "application/json": { "schema": { "allOf": [ { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, { "properties": { "data": { "type": "object", "description": "Represents an audio transcription result, following the OpenAI Whisper API response format. Contains the transcribed text along with optional metadata such as detected language, audio duration, word-level timestamps, and segment-level data.", "properties": { "text": { "type": "string", "readOnly": true, "description": "The full transcribed text output from the audio file." }, "language": { "type": "string", "readOnly": true, "description": "The detected or specified language code in ISO-639-1 format (e.g., \"en\" for English, \"es\" for Spanish, \"he\" for Hebrew)." }, "duration": { "type": "number", "readOnly": true, "description": "Total duration of the audio file in seconds (e.g., 3.5)." }, "words": { "type": "array", "readOnly": true, "description": "Word-level timestamps for each transcribed word. Only present when using the 'verbose_json' response format.", "items": { "type": "object", "properties": { "word": { "type": "string", "description": "The transcribed word." }, "start": { "type": "number", "description": "Start time of the word in seconds from the beginning of the audio." }, "end": { "type": "number", "description": "End time of the word in seconds from the beginning of the audio." } } } }, "segments": { "type": "array", "readOnly": true, "description": "Segment-level data with timing and optional speaker information. Each segment represents a contiguous block of transcribed speech, useful for diarization and long audio files.", "items": { "type": "object", "properties": { "id": { "type": "integer", "description": "Sequential identifier for the segment (e.g., 0, 1, 2)." }, "start": { "type": "number", "description": "Start time of the segment in seconds from the beginning of the audio." }, "end": { "type": "number", "description": "End time of the segment in seconds from the beginning of the audio." }, "text": { "type": "string", "description": "The transcribed text for this segment." }, "speaker": { "type": "string", "description": "Speaker identifier when diarization is enabled (e.g., \"SPEAKER_00\", \"SPEAKER_01\")." } } } } }, "required": [ "text" ], "example": { "text": "For more information visit www.FEMA.gov", "language": "en", "duration": 3.5, "words": [ { "word": "For", "start": 0, "end": 0.18 }, { "word": "more", "start": 0.18, "end": 0.38 }, { "word": "information", "start": 0.38, "end": 0.92 }, { "word": "visit", "start": 0.92, "end": 1.24 }, { "word": "www.FEMA.gov", "start": 1.24, "end": 3.5 } ], "segments": [ { "id": 0, "start": 0, "end": 3.5, "text": "For more information visit www.FEMA.gov", "speaker": "SPEAKER_00" } ] } } } } ] } } } }, "202": { "description": "Async mode: job queued successfully. Poll the returned run UID for the result.", "content": { "application/json": { "schema": { "allOf": [ { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, { "properties": { "data": { "type": "object", "description": "Represents an async transcription run. Poll this resource until status is COMPLETED or FAILED.", "properties": { "uid": { "type": "string", "readOnly": true, "description": "Unique identifier of the transcription run." }, "status": { "type": "string", "readOnly": true, "enum": [ "QUEUED", "IN_PROGRESS", "COMPLETED", "FAILED" ], "description": "Current status of the run. Possible values: 'QUEUED' (job is waiting to be processed), 'IN_PROGRESS' (job is actively being processed by the transcription provider), 'COMPLETED' (job finished successfully and result is available), 'FAILED' (job encountered an error and error_message is available)." }, "created_at": { "type": "string", "format": "date-time", "readOnly": true, "description": "The date and time when the run was created, in ISO 8601 format (e.g., \"2026-02-08T13:18:39.698Z\")." }, "updated_at": { "type": "string", "format": "date-time", "readOnly": true, "description": "The date and time when the run was last updated, in ISO 8601 format (e.g., \"2026-02-08T13:18:41.000Z\")." }, "result": { "type": "object", "description": "The transcription result. Only present when status is 'COMPLETED'.", "properties": { "text": { "type": "string", "readOnly": true, "description": "The full transcribed text output from the audio file." }, "language": { "type": "string", "readOnly": true, "description": "The detected or specified language code in ISO-639-1 format (e.g., \"en\" for English, \"es\" for Spanish, \"he\" for Hebrew)." }, "duration": { "type": "number", "readOnly": true, "description": "Total duration of the audio file in seconds (e.g., 3.5)." }, "words": { "type": "array", "readOnly": true, "description": "Word-level timestamps for each transcribed word. Only present when using the 'verbose_json' response format.", "items": { "type": "object", "properties": { "word": { "type": "string", "description": "The transcribed word." }, "start": { "type": "number", "description": "Start time of the word in seconds from the beginning of the audio." }, "end": { "type": "number", "description": "End time of the word in seconds from the beginning of the audio." } } } }, "segments": { "type": "array", "readOnly": true, "description": "Segment-level data with timing and optional speaker information. Each segment represents a contiguous block of transcribed speech, useful for diarization and long audio files.", "items": { "type": "object", "properties": { "id": { "type": "integer", "description": "Sequential identifier for the segment (e.g., 0, 1, 2)." }, "start": { "type": "number", "description": "Start time of the segment in seconds from the beginning of the audio." }, "end": { "type": "number", "description": "End time of the segment in seconds from the beginning of the audio." }, "text": { "type": "string", "description": "The transcribed text for this segment." }, "speaker": { "type": "string", "description": "Speaker identifier when diarization is enabled (e.g., \"SPEAKER_00\", \"SPEAKER_01\")." } } } } }, "required": [ "text" ], "example": { "text": "For more information visit www.FEMA.gov", "language": "en", "duration": 3.5, "words": [ { "word": "For", "start": 0, "end": 0.18 }, { "word": "more", "start": 0.18, "end": 0.38 }, { "word": "information", "start": 0.38, "end": 0.92 }, { "word": "visit", "start": 0.92, "end": 1.24 }, { "word": "www.FEMA.gov", "start": 1.24, "end": 3.5 } ], "segments": [ { "id": 0, "start": 0, "end": 3.5, "text": "For more information visit www.FEMA.gov", "speaker": "SPEAKER_00" } ] }, "readOnly": true }, "error_message": { "type": "string", "readOnly": true, "description": "Error message describing the failure reason. Only present when status is 'FAILED'." } }, "required": [ "uid", "status", "created_at" ], "example": { "uid": "85ade9f5-2690-48e8-ae5b-b07d6b57b457", "status": "COMPLETED", "created_at": "2026-02-08T13:18:39.698Z", "updated_at": "2026-02-08T13:18:41.000Z", "result": { "text": "For more information visit www.FEMA.gov", "language": "en", "duration": 3.5 } } } } } ] } } } }, "400": { "description": "Bad Request - The request is malformed or contains invalid syntax.", "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, "example": { "success": false, "errors": [ { "code": "invalid_syntax", "message": "Request body is malformed or missing required multipart form data." } ] } } } }, "401": { "description": "Unauthorized - The bearer token is missing, expired, or invalid.", "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, "example": { "success": false, "errors": [ { "code": "unauthorized", "message": "Invalid or expired bearer token." } ] } } } }, "413": { "description": "Payload Too Large - The uploaded audio file exceeds the 25MB size limit.", "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, "example": { "success": false, "errors": [ { "field": "file", "code": "too_large", "message": "File size exceeds the maximum allowed limit of 25MB." } ] } } } }, "422": { "description": "Unprocessable Entity - Validation error with valid syntax.", "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, "example": { "success": false, "errors": [ { "field": "model", "code": "invalid", "message": "Unsupported model. Supported models: openai/whisper-1, openai/gpt-4o-transcribe, google/chirp-2." } ] } } } }, "429": { "description": "Too Many Requests - Rate limit exceeded (10 requests per minute).", "content": { "application/json": { "schema": { "type": "object", "properties": { "success": { "type": "boolean", "description": "Indicates whether the API request was successful (true) or failed (false)." }, "data": { "type": "object", "description": "The response payload. Present on successful responses (success: true)." }, "error": { "type": "string", "description": "Error message for simple error responses. Used in some legacy endpoints." }, "errors": { "type": "array", "description": "Array of error objects for detailed error responses. Present on error responses (success: false).", "items": { "type": "object", "properties": { "code": { "type": "string", "description": "Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found')." }, "message": { "type": "string", "description": "Human-readable error message." }, "field": { "type": "string", "description": "The field that caused the error (for validation errors)." } }, "required": [ "code", "message" ] } } }, "required": [ "success" ], "description": "Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string." }, "example": { "success": false, "errors": [ { "code": "rate_limit_exceeded", "message": "Rate limit exceeded. Maximum 10 requests per minute. Please retry after 60 seconds." } ] } } } } }, "security": [ { "Bearer": [] } ] } } }, "components": { "securitySchemes": { "Bearer": { "type": "http", "scheme": "bearer", "bearerFormat": "JWT", "description": "Provide a valid bearer token in the Authorization header. Example: 'Authorization: Bearer {app_token}'" } } }, "tags": [ { "name": "AI Audio Transcriptions", "description": "Transcribe audio files using multiple providers" } ] } ```