> ## Documentation Index > Fetch the complete documentation index at: https://docs.voxnexus.ai/llms.txt > Use this file to discover all available pages before exploring further. # Speech to Text > Convert audio file to text, returns complete recognition result ## OpenAPI ````yaml /api-reference/openapi.yaml post /v1/stt openapi: 3.0.0 info: title: VoxNexus API version: 1.0.0 description: VoxNexus API Documentation contact: name: API Support url: https://voxnexus.ai/support email: support@voxnexus.ai servers: - url: https://api.voxnexus.ai security: [] paths: /v1/stt: post: tags: - stt summary: Speech to Text description: Convert audio file to text, returns complete recognition result operationId: speechToText parameters: - name: model_id in: query description: | Model identifier (required). Specifies which model to use for STT. required: true schema: type: string example: vn-stt-basic - name: language in: query description: > Language or locale code (optional, default: "en-US"). Supports both ISO 639-1 language codes (e.g. "en", "zh") and BCP 47 locale codes (e.g. "en-US", "zh-CN"). When a language code is provided, the system will automatically resolve it to the most common locale (e.g. "en" -> "en-US"). Improves recognition performance if provided, otherwise auto-detected by service. required: false schema: type: string default: en-US example: en-US - name: sample_rate in: query description: 'Sample rate (required, unit: Hz, e.g. 16000, 22050, 44100, 48000)' required: true schema: type: integer minimum: 1 example: 16000 - name: enable_timestamps in: query description: Whether to return timestamps (optional, default false) required: false schema: type: boolean default: false - name: enable_speaker_diarization in: query description: Whether to enable speaker diarization (optional, default false) required: false schema: type: boolean default: false - name: enable_llm_transform in: query description: > Whether to enable LLM post-processing on the STT transcript (optional, default false). When enabled, the recognized `transcript` is passed to the LLM with the specified `llm_prompt`, and the transformed result is returned in the `text` field. If LLM transform fails, `text` falls back to the raw transcript (no error is returned). **This feature requires whitelist access. Contact support@voxnexus.ai to request access.** required: false schema: type: boolean default: false - name: llm_prompt in: query description: > LLM transform instruction (required when `enable_llm_transform=true`). Describes what the LLM should do with the transcript, e.g. "correct punctuation", "rewrite in a humorous tone", "translate to English", "summarize key points". The LLM applies this instruction freely — the service does not interpret its semantics. required: false schema: type: string example: Correct punctuation and remove filler words - name: llm_model_id in: query description: > LLM model ID (optional). Falls back to the server-configured default model when not specified. Routing is prefix-based: `claude-*` models route to Anthropic; all other model IDs route to OpenAI. Examples: `claude-haiku-4-5-20251001` (Anthropic), `gpt-4.1` (OpenAI). required: false schema: type: string example: claude-haiku-4-5-20251001 - name: llm_max_tokens in: query description: > Maximum output tokens for LLM transform (optional). Falls back to the server default when not specified. required: false schema: type: integer minimum: 1 maximum: 4096 example: 1024 requestBody: required: true content: audio/wav: schema: type: string format: binary audio/mpeg: schema: type: string format: binary audio/pcm: schema: type: string format: binary application/octet-stream: schema: type: string format: binary responses: '200': description: Successfully returns recognition result headers: X-Request-ID: schema: type: string description: Request ID X-Language: schema: type: string description: Detected language code X-Duration-Ms: schema: type: integer description: Audio duration in milliseconds content: application/json: schema: $ref: '#/components/schemas/STTResponse' '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Insufficient credits or rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - ApiKeyAuth: [] components: schemas: STTResponse: type: object properties: request_id: type: string description: Request ID example: req_1234567890 language: type: string description: Detected language code, e.g. en, en-US example: en transcript: type: string description: > Raw STT recognition output (original ASR text before any LLM processing). Always present; identical to `text` when LLM transform is not enabled. example: Hello this is a test message text: type: string description: > Final output text. When LLM transform is enabled and succeeds, this contains the LLM-transformed result; otherwise it equals `transcript`. example: Hello, this is a test message. duration_ms: type: integer description: Audio duration in milliseconds example: 2500 words: type: array description: Word-level information (if timestamps are enabled) items: $ref: '#/components/schemas/STTWordInfo' speakers: type: array description: Speaker information (if speaker diarization is enabled) items: $ref: '#/components/schemas/STTSpeakerInfo' created_at: type: string format: date-time description: Creation time example: '2024-01-01T12:00:00Z' required: - request_id - transcript - text - duration_ms - created_at ErrorResponse: type: object properties: error: type: string description: Error message example: Invalid request parameters code: type: string description: Error code example: INVALID_REQUEST details: type: string description: Detailed error information (optional) example: Detailed error information request_id: type: string description: Request ID (optional) example: req_1234567890 required: - error STTWordInfo: type: object properties: word: type: string description: Word example: hello offset: type: integer description: Word offset in audio stream (milliseconds) example: 0 duration: type: integer description: Word duration (milliseconds) example: 500 confidence: type: number format: float description: Confidence score 0.0-1.0 minimum: 0 maximum: 1 example: 0.98 required: - word STTSpeakerInfo: type: object properties: speaker_id: type: string description: Speaker ID example: speaker_1 text: type: string description: Text spoken by this speaker example: Hello, this is a test message. offset: type: integer description: Speaker text offset in audio stream (milliseconds) example: 0 duration: type: integer description: Speaker text duration (milliseconds) example: 2500 required: - speaker_id - text securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-Api-Key description: Authenticate using X-Api-Key header ````