xai/grok-voice-asr

grok-voice-asr
文档
Schema

[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.

$0.0001/sec
speech-to-text

输入

Public http(s) URL of the audio file for transcription. File upload is not supported.
提示：可拖拽文件、从剪贴板粘贴（Ctrl/Cmd+V），或提供 URL。
Key terms to bias transcription toward (product names, proper nouns). Max 100 terms, each up to 50 characters.
Format hint for raw/headerless audio only. Do not set for MP3/WAV/etc. Requires sample_rate when set.
audio_format
Number of channels for multichannel raw audio (2–8). Container formats are usually auto-detected.
When true, enables speaker diarization; words include speaker ids.
When true, keep filler words (uh/um/er) in the transcript.
When true, enables Inverse Text Normalization (e.g. spoken numbers to written form). Requires language.
Language code for Inverse Text Normalization when format=true. Required when format is true.
language
When true, transcribes each audio channel independently.
Sample rate in Hz for raw audio. Required when audio_format is set.
sample_rate

结果

暂无结果

运行模型后，结果将在这里显示。

Next:

README

属性

系列

参数

参数名 描述 类型 必填 枚举值
url Public http(s) URL of the audio file for transcription. File upload is not supported. string 是 -
keyterm Key terms to bias transcription toward (product names, proper nouns). Max 100 terms, each up to 50 characters. string[] 否 -
audio_format Format hint for raw/headerless audio only. Do not set for MP3/WAV/etc. Requires sample_rate when set. string 否 pcm, mulaw, alaw
channels Number of channels for multichannel raw audio (2–8). Container formats are usually auto-detected. integer 否 -
diarize When true, enables speaker diarization; words include speaker ids. boolean 否 true, false
filler_words When true, keep filler words (uh/um/er) in the transcript. boolean 否 true, false
format When true, enables Inverse Text Normalization (e.g. spoken numbers to written form). Requires language. boolean 否 true, false
language Language code for Inverse Text Normalization when format=true. Required when format is true. string 否 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
multichannel When true, transcribes each audio channel independently. boolean 否 true, false
sample_rate Sample rate in Hz for raw audio. Required when audio_format is set. integer 否 8000, 16000, 22050, 24000, 44100, 48000

价格

单位: $/sec

价格
$0.0001/sec

相关模型

  • xai/grok-voice-tts: [Core Function] Grok Voice TTS converts text into natural spoken audio with expressive voices and optional speech tags embedded in the text. [Strengths] Supports 20+ languages (plus auto-detect), 26 built-in voices, multiple codecs (mp3/wav/pcm/mulaw/alaw), and custom voice IDs. [Best For] Product voiceovers, IVR/telephony (mulaw/alaw), and multilingual narration. [Limitations] Do NOT exceed 15,000 characters per request. Audio is returned on the completed task after polling. [Routing] Use this model for xAI Grok Voice quality or custom cloned voices. [Built-in voices] Original: eve (default), ara, leo, rex, sal. Flagship: altair, atlas, carina, castor, celeste, cosmo, helios, helix, iris, kepler, lumen, luna, lux, naksh, orion, perseus, rigel, sirius, ursa, zagan, zenith — case-insensitive; custom voice IDs are also accepted as voice_id.

相关资源

Grok Voice
Grok VoiceSeries
xai/grok-voice-tts
xai/grok-voice-ttstext-to-speech