> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # Grok Voice ASR > [Core Function] Grok Voice ASR transcribes a single public audio URL into text via an async task. [Strengths] Word-level timestamps, optional speaker diarization, multichannel transcription, Inverse Text Normalization (format + language), keyterm biasing, and filler-word control. [Best For] Meeting notes, call-center recordings, captions, and batch audio-to-text pipelines. [Limitations] Do NOT use file upload; URL-only input. Do NOT use for live or real-time streaming transcription. Audio must be publicly reachable (max 500 MB). [Routing] Use this model for xAI Grok Voice ASR quality with URL-based audio. ## OpenAPI ````yaml /media-model-api/xai/xai-s2t.json post /xai/grok-voice-asr openapi: 3.1.0 info: title: xAI Grok Voice Speech-to-Text API description: >- xAI Grok Voice speech-to-text. Submit a public audio URL as an async task; poll GET /api/v1/tasks/{task_id} for the transcription result. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: xAI Grok Voice speech-to-text models API security: - bearerAuth: [] paths: /xai/grok-voice-asr: post: summary: Grok Voice ASR description: >- [Core Function] Grok Voice ASR transcribes a single public audio URL into text via an async task. [Strengths] Word-level timestamps, optional speaker diarization, multichannel transcription, Inverse Text Normalization (format + language), keyterm biasing, and filler-word control. [Best For] Meeting notes, call-center recordings, captions, and batch audio-to-text pipelines. [Limitations] Do NOT use file upload; URL-only input. Do NOT use for live or real-time streaming transcription. Audio must be publicly reachable (max 500 MB). [Routing] Use this model for xAI Grok Voice ASR quality with URL-based audio. operationId: grokVoiceASR requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GrokVoiceASRRequest' examples: basic: summary: Minimal request value: url: https://cdn.example.com/meeting.mp3 formatted: summary: ITN formatting with language value: url: https://cdn.example.com/meeting.mp3 language: en format: true keyterm: - Modellix - Grok diarize: summary: Speaker diarization value: url: https://cdn.example.com/call.wav diarize: true filler_words: false responses: '200': description: >- Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; the transcription result is returned on the task result. content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-grok-voice-asr-001 model_id: xai/grok-voice-asr get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-grok-voice-asr-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: GrokVoiceASRRequest: type: object required: - url additionalProperties: false properties: url: type: string minLength: 1 pattern: ^https?:// description: >- Public http(s) URL of the audio file for transcription. File upload is not supported. language: type: string enum: - ar - cs - da - nl - en - fil - fr - de - hi - id - it - ja - ko - mk - ms - fa - pl - pt - ro - ru - es - sv - th - tr - vi description: >- Language code for Inverse Text Normalization when format=true. Required when format is true. format: type: boolean default: false description: >- When true, enables Inverse Text Normalization (e.g. spoken numbers to written form). Requires language. multichannel: type: boolean default: false description: When true, transcribes each audio channel independently. channels: type: integer minimum: 2 maximum: 8 description: >- Number of channels for multichannel raw audio (2–8). Container formats are usually auto-detected. diarize: type: boolean default: false description: When true, enables speaker diarization; words include speaker ids. keyterm: type: array maxItems: 100 items: type: string maxLength: 50 description: >- Key terms to bias transcription toward (product names, proper nouns). Max 100 terms, each up to 50 characters. filler_words: type: boolean default: false description: When true, keep filler words (uh/um/er) in the transcript. audio_format: type: string enum: - pcm - mulaw - alaw description: >- Format hint for raw/headerless audio only. Do not set for MP3/WAV/etc. Requires sample_rate when set. sample_rate: type: integer enum: - 8000 - 16000 - 22050 - 24000 - 44100 - 48000 description: Sample rate in Hz for raw audio. Required when audio_format is set. AsyncTaskResponse: description: Response object for asynchronous task submission. type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id description: >- Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; the transcription appears in result.resources. See Common API: Query Task Result. properties: status: type: string enum: - pending - processing description: Initial task status example: pending task_id: type: string description: Unique task identifier for polling example: task-grok-voice-asr-001 model_id: type: string description: Model ID in provider/model format example: xai/grok-voice-asr get_result: type: object description: >- Endpoint to query the task result. See Common API: Query Task Result. properties: method: type: string example: GET url: type: string example: https://api.modellix.ai/api/v1/tasks/task-grok-voice-asr-001 responses: BadRequest: description: Invalid parameters Unauthorized: description: Missing or invalid API key TooManyRequests: description: Rate limited InternalServerError: description: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer ````