{"servers":[{"url":"https://api.modellix.ai/api/v1/xai/grok-voice-asr"}],"post":{"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":{"content":{"application/json":{"examples":{"basic":{"summary":"Minimal request","value":{"url":"https://cdn.example.com/meeting.mp3"}},"diarize":{"summary":"Speaker diarization","value":{"diarize":true,"filler_words":false,"url":"https://cdn.example.com/call.wav"}},"formatted":{"summary":"ITN formatting with language","value":{"format":true,"keyterm":["Modellix","Grok"],"language":"en","url":"https://cdn.example.com/meeting.mp3"}}},"schema":{"additionalProperties":false,"properties":{"audio_format":{"description":"Format hint for raw/headerless audio only. Do not set for MP3/WAV/etc. Requires sample_rate when set.","enum":["pcm","mulaw","alaw"],"type":"string"},"channels":{"description":"Number of channels for multichannel raw audio (2–8). Container formats are usually auto-detected.","maximum":8,"minimum":2,"type":"integer"},"diarize":{"default":false,"description":"When true, enables speaker diarization; words include speaker ids.","type":"boolean"},"filler_words":{"default":false,"description":"When true, keep filler words (uh/um/er) in the transcript.","type":"boolean"},"format":{"default":false,"description":"When true, enables Inverse Text Normalization (e.g. spoken numbers to written form). Requires language.","type":"boolean"},"keyterm":{"description":"Key terms to bias transcription toward (product names, proper nouns). Max 100 terms, each up to 50 characters.","items":{"maxLength":50,"type":"string"},"maxItems":100,"type":"array"},"language":{"description":"Language code for Inverse Text Normalization when format=true. Required when format is true.","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"],"type":"string"},"multichannel":{"default":false,"description":"When true, transcribes each audio channel independently.","type":"boolean"},"sample_rate":{"description":"Sample rate in Hz for raw audio. Required when audio_format is set.","enum":[8000,16000,22050,24000,44100,48000],"type":"integer"},"url":{"description":"Public http(s) URL of the audio file for transcription. File upload is not supported.","minLength":1,"pattern":"^https?://","type":"string"}},"required":["url"],"type":"object"}}},"required":true},"responses":{"200":{"content":{"application/json":{"example":{"code":0,"data":{"get_result":{"method":"GET","url":"https://api.modellix.ai/api/v1/tasks/task-grok-voice-asr-001"},"model_id":"xai/grok-voice-asr","status":"pending","task_id":"task-grok-voice-asr-001"},"message":"success"},"schema":{"description":"Response object for asynchronous task submission.","properties":{"code":{"description":"Response code, 0 indicates success","example":0,"type":"integer"},"data":{"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":{"get_result":{"description":"Endpoint to query the task result. See Common API: Query Task Result.","properties":{"method":{"example":"GET","type":"string"},"url":{"example":"https://api.modellix.ai/api/v1/tasks/task-grok-voice-asr-001","type":"string"}},"type":"object"},"model_id":{"description":"Model ID in provider/model format","example":"xai/grok-voice-asr","type":"string"},"status":{"description":"Initial task status","enum":["pending","processing"],"example":"pending","type":"string"},"task_id":{"description":"Unique task identifier for polling","example":"task-grok-voice-asr-001","type":"string"}},"required":["status","task_id","model_id"],"type":"object"},"message":{"description":"Response message","example":"success","type":"string"}},"required":["code","message","data"],"type":"object"}}},"description":"Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; the transcription result is returned on the task result."},"400":{"description":"Invalid parameters"},"401":{"description":"Missing or invalid API key"},"429":{"description":"Rate limited"},"500":{"description":"Internal server error"}},"summary":"Grok Voice ASR","x-mint":{"href":"xai/grok-voice-asr"}}}