> ## Documentation Index > Fetch the complete documentation index at: https://platform.minimax.io/docs/llms.txt > Use this file to discover all available pages before exploring further. # Speech to Text > Use this API to transcribe an audio file into text, with support for streaming output, speaker diarization and subtitle export. ## OpenAPI ````yaml api-reference/speech/speech-to-text/api/openapi.json POST /v1/speech_to_text openapi: 3.1.0 info: title: MiniMax ASR API description: MiniMax Speech-to-Text API with support for one-shot and streaming output license: name: MIT version: 1.0.0 servers: - url: https://api.minimax.io security: - bearerAuth: [] paths: /v1/speech_to_text: post: tags: - SpeechToText summary: Speech to Text operationId: speechToText parameters: - name: Content-Type in: header required: true description: The media type of the request body. Must be `multipart/form-data`. schema: type: string enum: - multipart/form-data default: multipart/form-data - name: language in: header required: false description: >- An optional [BCP-47 language tag](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) that hints at the primary spoken language. Omit this header or pass an empty value to enable mixed-language recognition. Currently supported values: `zh` (Chinese), `yue` (Cantonese), `en` (English), `ja` (Japanese), `ko` (Korean), `th` (Thai), `vi` (Vietnamese), `id` (Indonesian), `ms` (Malay), `fil` (Filipino), `ar` (Arabic), `tr` (Turkish), `fr` (French), `de` (German), `es` (Spanish), `it` (Italian), `pt` (Portuguese), `pl` (Polish), `ru` (Russian), and `uk` (Ukrainian). schema: type: string default: '' example: en requestBody: required: true content: multipart/form-data: schema: type: object required: - model - file properties: model: type: string description: The model version used for this request. enum: - asr-1.0 default: asr-1.0 example: asr-1.0 file: type: string format: binary description: >- The audio file to transcribe. Provide the path to the file. The uploaded audio file must meet the following requirements: | Item | Constraint | | --- | --- | | Format | `wav` / `aiff` / `flac` / `alac`(m4a) / `mp3` / `aac` / `opus` / `ogg` | | Duration | No longer than **500 seconds**. Exceeding this returns `400`; the audio is never silently truncated | | Size | No larger than **50 MB**. Exceeding this returns `413` | Raw PCM without a container is not supported. Speech recognition does not benefit from high sample rates or stereo. Uncompressed high-specification audio easily exceeds the size limit (for example, 500 seconds of 48 kHz stereo WAV is about 92 MB). Convert to mono 16 kHz, or use a compressed format such as `mp3` / `aac` / `opus`; the transcription result is unaffected. response_format: type: string description: >- The format of the transcription result. | Value | Returns | Response type | | --- | --- | --- | | `json` | `text` + `duration` | `application/json` | | `verbose_json` | `text` + `duration` + `segments` + `n_speakers` (includes speaker diarization and timestamps) | `application/json` | | `srt` | SRT subtitles | `text/plain` | | `vtt` | WebVTT subtitles | `text/vtt` | `verbose_json` / `srt` / `vtt` enable speaker diarization and forced alignment, and therefore **cannot be combined with `stream=true`**. Response body for `srt`: ``` 1 00:00:00,100 --> 00:00:01,660 Hello everyone. 2 00:00:02,000 --> 00:00:06,100 Let me check the question. ``` Response body for `vtt`: ``` WEBVTT 00:00:00.100 --> 00:00:01.660 Hello everyone. 00:00:02.000 --> 00:00:06.100 Let me check the question. ``` enum: - json - verbose_json - srt - vtt default: json example: json stream: type: boolean description: >- Whether to stream the transcription result. - `false` (default): the full result is returned once transcription completes. - `true`: incremental text is pushed over SSE and the response type is `text/event-stream`. In this case `response_format` only supports `json`. A streaming response is pushed line by line as `data: `, with events separated by blank lines: ``` data: {"index":0,"delta":"Hello","finish":false} data: {"index":1,"delta":" everyone","finish":false} data: {"index":2,"delta":"","finish":true,"duration":26.325} ``` The `data` field of each event is a JSON object: `index` is the event sequence number starting from `0`, `delta` is the newly transcribed text for this event, `finish` indicates whether this is the terminating event, and `duration` is the audio duration in seconds (returned only in the terminating event). Clients should concatenate all `delta` values in `index` order and stop reading after receiving `finish=true`. default: false example: false responses: '200': description: >- Transcription succeeded. The fields below apply when `response_format` is `json` or `verbose_json`. For the response body of `srt` / `vtt` or `stream=true`, see the description of the corresponding request parameter. content: application/json: schema: $ref: '#/components/schemas/AsrResp' examples: json: summary: response_format=json value: text: >- The merchant actually made money, because their cold chain shipping is expensive. duration: 26.325 trace_id: 021785229015510a2c883cf675b9804d verbose_json: summary: response_format=verbose_json value: text: Hello everyone. Let me check the question. duration: 12.744 n_speakers: 2 segments: - id: 0 start: 0.1 end: 1.66 speaker: S1 text: Hello everyone. - id: 1 start: 2 end: 6.1 speaker: S2 text: Let me check the question. trace_id: 021785229015510a2c883cf675b9804d '400': $ref: '#/components/responses/Err400' '401': $ref: '#/components/responses/Err401' '402': $ref: '#/components/responses/Err402' '413': $ref: '#/components/responses/Err413' '422': $ref: '#/components/responses/Err422' '429': $ref: '#/components/responses/Err429' '500': $ref: '#/components/responses/Err500' components: schemas: AsrResp: type: object properties: text: type: string description: >- The full transcribed text. Under `verbose_json` this equals the concatenation of all `segments[].text` in time order. duration: type: number description: >- The duration of the input audio, in seconds. Billing is based on this duration. n_speakers: type: integer description: >- The number of detected speakers. **Returned only when `response_format=verbose_json`.** segments: type: array description: >- Sentence-level transcription results, each carrying start/end times and a speaker identifier. **Returned only when `response_format=verbose_json`.** items: $ref: '#/components/schemas/AsrSegment' trace_id: type: string description: The trace ID of this request, useful for troubleshooting. AsrSegment: type: object properties: id: type: integer description: The index of this sentence in the result, starting from `0`. start: type: number description: The start time of this sentence, in seconds. end: type: number description: The end time of this sentence, in seconds. speaker: type: string description: >- The speaker identifier, such as `S1` or `S2`. The same identifier denotes the same speaker. text: type: string description: The transcribed text of this sentence. OaiError: type: object description: >- OpenAI-style error response. On failure the HTTP status code is the real error code (401/400/429/402/413/422/500 and so on) and the response body follows this structure. properties: type: type: string description: Always `error`. example: error error: $ref: '#/components/schemas/OaiErrorDetail' request_id: type: string description: The request trace ID, useful for troubleshooting. OaiErrorDetail: type: object properties: type: type: string description: >- The error type: `authorized_error`(401) / `bad_request_error`(400) / `rate_limit_error`(429) / `insufficient_balance_error`(402) / `unprocessable_entity_error`(422) / `invalid_request_error`(413) / `server_error`(500) and so on. message: type: string description: >- The error detail. The value in parentheses at the end is the internal error code (for example `... (1004)`). http_code: type: string description: The HTTP status code as a string, for example `401`. responses: Err400: description: Invalid parameters content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: bad_request_error message: >- invalid params, audio duration 623.4s exceeds the limit of 500s (2013) http_code: '400' request_id: 021785229015510a2c883cf675b9804d Err401: description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: authorized_error message: >- login fail: Please carry the API secret key in the 'Authorization' field of the request header (1004) http_code: '401' request_id: 021785229015510a2c883cf675b9804d Err402: description: Insufficient balance or quota content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: insufficient_balance_error message: insufficient balance (1008) http_code: '402' request_id: 021785229015510a2c883cf675b9804d Err413: description: Request body exceeds the size limit content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: invalid_request_error message: >- request body too large: 88200078 bytes exceeds limit of 52428800 bytes http_code: '413' request_id: 021785229015510a2c883cf675b9804d Err422: description: Input contains sensitive content content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: unprocessable_entity_error message: audio content contains sensitive content (1026) http_code: '422' request_id: 021785229015510a2c883cf675b9804d Err429: description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: rate_limit_error message: rate limit, please retry later (1002) http_code: '429' request_id: 021785229015510a2c883cf675b9804d Err500: description: Server error content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: server_error message: internal error (1000) http_code: '500' request_id: 021785229015510a2c883cf675b9804d securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: |- `HTTP: Bearer Auth` - Security Scheme Type: http - HTTP Authorization Scheme: Bearer API_key, used to verify account information. You can view it in [Account Management > API Key](https://platform.minimax.io/user-center/basic-information/interface-key). ````