> ## Documentation Index > Fetch the complete documentation index at: https://docs.chariot.in/llms.txt > Use this file to discover all available pages before exploring further. # Transcribe a file > Upload a recording or provide an audio URL and receive a complete transcript. ## OpenAPI ````yaml api-reference/openapi.json POST /v1/asr/transcribe openapi: 3.1.0 info: title: Chariot API version: '1' description: >- Chariot is a voice AI platform built for Indian and English languages. Convert text into natural-sounding speech over a simple REST call, an HTTP audio stream, or a low-latency WebSocket, and transcribe speech to text over a streaming WebSocket or from a prerecorded file (Beta). This reference documents the public, API-key-authenticated endpoints. contact: name: Chariot Support email: support@chariot.in url: https://chariot.in servers: - url: https://api.chariot.in description: Production security: - APIKeyHeader: [] tags: - name: Text to Speech description: Convert text into speech synchronously or as a stream. - name: Speech to Text description: >- Transcribe prerecorded files (Beta) and review streaming speech-to-text sessions. - name: Voices description: Browse the voice catalog. - name: Account description: Inspect your credit balance and usage. paths: /v1/asr/transcribe: post: tags: - Speech to Text summary: Transcribe a file description: >- **Beta.** Transcribe one prerecorded audio or video file and receive the complete transcript in the same HTTP response. Send exactly one of `input_audio_file` or `input_audio_url` as multipart form data. Optional `model_type`, `language`, `style`, and `include_timestamps` fields apply to either input. File transcription defaults to `mode=high_accuracy` and rejects `balanced`; live WebSocket sessions still support both modes. Let your HTTP client set the multipart boundary. This is synchronous file transcription. Keep the request open until it completes. It does not create a durable background job or accept multiple files or CSV uploads. A retry is a new transcription request. Set include_timestamps=true for estimated word timings. Confidence scores and speaker labels are not returned. For durable jobs and multiple recordings, use POST /v1/asr/batches. See the [File transcription guide](/guides/speech-to-text/file-transcription) for upload and URL examples. File acceptance constraints can change during beta; handle validation responses rather than assuming every recording is accepted. operationId: transcribeFile requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/ASRFileTranscriptionRequest' responses: '200': description: Complete transcription. content: application/json: schema: $ref: '#/components/schemas/ASRFileTranscriptionResponse' example: request_id: a38c6b32-1f3a-4f02-a779-478282bce082 created: '2026-10-23T07:00:00Z' text: Hi, I'd like to move the meeting to Thursday. duration: 4.82 words: [] model_type: chariot-1-asr-realtime '401': $ref: '#/components/responses/Unauthorized' '402': description: Insufficient credits for this recording. content: application/json: schema: $ref: '#/components/schemas/Error' '403': description: ASR is not permitted by the current plan. content: application/json: schema: $ref: '#/components/schemas/Error' '413': description: The upload is too large. content: application/json: schema: type: object properties: detail: type: string description: Explanation of the upload rejection. required: - detail '422': description: >- Invalid input or transcription settings. Supply exactly one input and a readable audio track. A supplied URL must be accessible and the recording must meet the current file acceptance constraints. content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: >- Too many simultaneous ASR requests. Reduce concurrency and retry with backoff. content: application/json: schema: $ref: '#/components/schemas/Error' '502': description: Transcription failed while processing the recording. content: application/json: schema: $ref: '#/components/schemas/Error' '503': description: >- File transcription or the selected settings are temporarily unavailable. content: application/json: schema: $ref: '#/components/schemas/Error' '504': description: Transcription did not complete before the service timeout. content: application/json: schema: $ref: '#/components/schemas/Error' x-codeSamples: - lang: bash label: Upload a file source: |- curl --fail-with-body https://api.chariot.in/v1/asr/transcribe \ -H "chariotai-api-key: $CHARIOT_API_KEY" \ -F "input_audio_file=@recording.wav" - lang: bash label: Use a URL source: |- curl --fail-with-body https://api.chariot.in/v1/asr/transcribe \ -H "chariotai-api-key: $CHARIOT_API_KEY" \ --form-string "input_audio_url=$AUDIO_URL" components: schemas: ASRFileTranscriptionRequest: type: object description: >- Send exactly one of input_audio_file or input_audio_url as multipart/form-data. Other fields apply to either input. oneOf: - title: File upload type: object required: - input_audio_file properties: input_audio_file: type: string format: binary description: >- The audio or video file bytes. The file must contain a readable audio track. Supply this or input_audio_url, not both. language: type: string enum: - none - en - hi - bn - gu - kn - ml - mr - or - pa - sa - ta - te default: none description: >- Requested transcription language. Omit or use none for automatic detection. This does not request translation. mode: type: string enum: - high_accuracy default: high_accuracy description: >- File transcription always uses high_accuracy. balanced is only supported by the live WebSocket. style: type: string enum: - codemix - native default: codemix description: >- Writing style for mixed-language speech. codemix keeps borrowed words in their own script; native writes them in the spoken language's script. include_timestamps: type: boolean default: false description: >- Return estimated word timestamps in seconds from the start of the file. Applies to either file upload or URL input. model_type: type: string enum: - chariot-1-asr-realtime default: chariot-1-asr-realtime description: >- Public ASR model. The same model_type is used across WebSocket, file and batch transcription. not: required: - input_audio_url - title: Media URL type: object required: - input_audio_url properties: input_audio_url: type: string format: uri minLength: 1 description: >- Direct HTTP or HTTPS media URL reachable by Chariot, including a signed URL. It must remain valid during download and must not require additional authentication headers. Supply this or input_audio_file, not both. language: type: string enum: - none - en - hi - bn - gu - kn - ml - mr - or - pa - sa - ta - te default: none description: >- Requested transcription language. Omit or use none for automatic detection. This does not request translation. mode: type: string enum: - high_accuracy default: high_accuracy description: >- File transcription always uses high_accuracy. balanced is only supported by the live WebSocket. style: type: string enum: - codemix - native default: codemix description: >- Writing style for mixed-language speech. codemix keeps borrowed words in their own script; native writes them in the spoken language's script. include_timestamps: type: boolean default: false description: >- Return estimated word timestamps in seconds from the start of the file. Applies to either file upload or URL input. model_type: type: string enum: - chariot-1-asr-realtime default: chariot-1-asr-realtime description: >- Public ASR model. The same model_type is used across WebSocket, file and batch transcription. not: required: - input_audio_file ASRFileTranscriptionResponse: description: One complete file transcript; uploaded channels are mixed to mono. properties: model_type: $ref: '#/components/schemas/ASRFileASRModelType' default: chariot-1-asr-realtime request_id: description: Identifier for this transcription request. title: Request Id type: string created: description: Response creation time in UTC. format: date-time title: Created type: string text: description: Complete recognized text, empty when no speech is recognized. title: Text type: string duration: description: Processed audio duration in seconds, not request latency. title: Duration type: number words: anyOf: - items: $ref: '#/components/schemas/ASRFileASRWordTimestamp' type: array - type: 'null' description: >- Estimated word boundaries in seconds from the start of the file when include_timestamps=true. Null when requested but unavailable or invalid; an empty list means no timed words. Also empty when timestamps are not requested. title: Words required: - request_id - created - text - duration title: ASRResponse type: object Error: type: object description: Standard error envelope returned by all endpoints. properties: statusCode: type: integer description: HTTP status code, echoed in the body. error: type: string description: Machine-readable error class name. message: type: string description: Human-readable description of what went wrong. required: - statusCode - error - message ASRFileASRModelType: description: >- Public streaming ASR ``model_type`` values, the same parameter name TTS uses. A product name, never the checkpoint or serving name behind it: the upstream's served name is configuration and is never sent to a caller. enum: - chariot-1-asr-realtime title: ASRModelType type: string ASRFileASRWordTimestamp: description: Estimated word boundaries in seconds from the start of session audio. properties: text: title: Text type: string start: minimum: 0 title: Start type: number end: minimum: 0 title: End type: number required: - text - start - end title: ASRWordTimestamp type: object responses: Unauthorized: description: Authentication failed. The API key is missing, invalid, or expired. content: application/json: schema: $ref: '#/components/schemas/Error' examples: missing: summary: No credentials provided value: statusCode: 401 error: UnauthorizedException message: No API key or user credentials provided invalid: summary: Invalid or unknown API key value: statusCode: 401 error: UnauthorizedException message: Invalid API Key or user credentials securitySchemes: APIKeyHeader: type: apiKey in: header name: chariotai-api-key description: >- Your Chariot API key, generated from the dashboard. Send it in the `chariotai-api-key` header on every request. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.