> ## Documentation Index > Fetch the complete documentation index at: https://docs.near.ai/llms.txt > Use this file to discover all available pages before exploring further. # Audio transcription endpoint > Transcribe audio files using Whisper models. Accepts audio file uploads via multipart/form-data. Supports MP3, WAV, WEBM, FLAC, OGG, and M4A formats. Maximum file size: 25 MB. **Request Body (multipart/form-data):** All fields should be provided as text values or files as indicated in the schema. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/audio/transcriptions openapi: 3.1.0 info: title: NEAR AI Cloud API description: >- NEAR AI Cloud API for private AI model inference and organization administration. contact: name: NEAR AI Team email: support@near.ai license: name: MIT version: 1.0.0 servers: - url: https://cloud-api.near.ai description: NEAR AI Cloud security: - session_token: [] - api_key: [] tags: - name: Chat description: Chat completion endpoints for AI model inference - name: Images description: Image generation endpoints - name: Audio description: Audio transcription endpoints - name: Rerank description: Document reranking endpoints - name: Score description: Text similarity scoring endpoints - name: Privacy description: Privacy classification (PII span detection) endpoints - name: Models description: Public model catalog and information - name: Responses description: >- Stateless response inference (`store: false` only). Raw request/response content, response items, and history are not persisted. Clients must include any prior context in each request. Every successful Responses inference makes exactly one Chat Completions call. Only custom `function` tools are supported. They are client-managed: Cloud returns `function_call` items but never executes them; a later `store: false` request replays the individual call (the raw item from output is accepted) with its matching `function_call_output`, alongside caller-managed message history and the same function tool definitions. The minimal replay path also accepts assistant `message` text parts of type `output_text`, but not reasoning or arbitrary full `response.output` items. Server-executed tools (`web_search`, `web_context_search`, `file_search`, `code_interpreter`, `computer`, and remote `mcp`) and image-generation/editing models are rejected. The separate `POST /mcp` endpoint continues to expose its `web_search` tool independently of Responses; use `/v1/images/*` for image generation/editing. Existing completed-response gateway attestation is preserved best-effort: when the signature write succeeds, `GET /v1/signature/resp_*` retrieves signatures over SHA-256 request/response digests, never raw content. Interrupted streams create no `resp_*` attestation record or legacy disconnect fallback. Conversations, response history, and file input are rejected. - name: Organizations description: Organization management - name: Organization Members description: Organization member and invitation management - name: Workspaces description: Workspace and API key management - name: Users description: User profile and token management - name: Invitations description: Token-based invitation handling - name: Usage description: Usage tracking and billing information - name: Reporting description: Read-only customer usage reporting - name: Billing description: Billing costs endpoint (HuggingFace integration) - name: Staking Farm description: House of Stake farm credit configuration and synchronization - name: Health description: Health check endpoints - name: Attestation description: Attestation and verification endpoints - name: Gateway description: Model gateway integration endpoints - name: Admin description: Administrative endpoints (admin access required) - name: Services description: Public platform services (e.g. web_search pricing) paths: /v1/audio/transcriptions: post: tags: - Audio summary: Audio transcription endpoint description: >- Transcribe audio files using Whisper models. Accepts audio file uploads via multipart/form-data. Supports MP3, WAV, WEBM, FLAC, OGG, and M4A formats. Maximum file size: 25 MB. **Request Body (multipart/form-data):** All fields should be provided as text values or files as indicated in the schema. operationId: audio_transcriptions requestBody: content: multipart/form-data: schema: $ref: '#/components/schemas/AudioTranscriptionRequestSchema' required: true responses: '200': description: Successful transcription content: application/json: schema: $ref: '#/components/schemas/AudioTranscriptionResponse' text/plain: schema: type: string '400': description: Invalid request (empty file, unsupported format, file too large) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized (missing or invalid API key) content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Model not found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: >- Rate limited or overloaded — retry with backoff. Check error.type: rate_limit_exceeded or service_overloaded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - ApiKeyAuth: [] components: schemas: AudioTranscriptionRequestSchema: type: object description: |- Audio transcription request schema for OpenAPI documentation This represents the multipart/form-data fields required: - file - model properties: file: type: string description: Audio file (required) - binary audio data language: type: - string - 'null' description: Language code (optional) - e.g. "en", "es" model: type: string description: Model identifier (required) - e.g. "openai/whisper-large-v3" response_format: type: - string - 'null' description: 'Response format (optional) - one of: "json", "text", "verbose_json"' timestamp_granularities: type: - array - 'null' items: type: string description: >- Timestamp granularities (optional) - supports "segment" and "word" with verbose_json. Multipart requests may send repeated timestamp_granularities[] fields, repeated timestamp_granularities fields, or comma-separated values. AudioTranscriptionResponse: type: object description: Audio transcription response (with OpenAPI schema) required: - text properties: duration: type: - number - 'null' format: double description: Total audio duration in seconds language: type: - string - 'null' description: Detected language code segments: type: - array - 'null' items: $ref: '#/components/schemas/TranscriptionSegment' description: Transcription segments with timing text: type: string description: Transcribed text words: type: - array - 'null' items: $ref: '#/components/schemas/TranscriptionWord' description: Word-level timing information ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' TranscriptionSegment: type: object description: >- Transcription segment with optional metadata fields Matches the inference_providers version to ensure consistency with actual provider responses required: - id - seek - start - end - text - tokens - temperature properties: avg_logprob: type: - number - 'null' format: double description: 'Optional: may be null in some provider responses' compression_ratio: type: - number - 'null' format: double description: 'Optional: may be null in some provider responses' end: type: number format: double id: type: integer format: int32 no_speech_prob: type: - number - 'null' format: double description: 'Optional: may be null in some provider responses' seek: type: integer format: int32 start: type: number format: double temperature: type: number format: double text: type: string tokens: type: array items: type: integer format: int32 TranscriptionWord: type: object description: Word-level timing information required: - word - start - end properties: end: type: number format: double start: type: number format: double word: type: string ErrorDetail: type: object required: - message - type properties: code: type: - string - 'null' message: type: string param: type: - string - 'null' type: type: string securitySchemes: session_token: type: http scheme: bearer bearerFormat: JWT description: >- JWT access token for user authentication (Authorization: Bearer ). Create via POST /users/me/access_tokens. api_key: type: http scheme: bearer bearerFormat: api_key description: 'API key for programmatic access (Authorization: Bearer sk-)' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.