属性
系列
参数
| 参数名 | 描述 | 类型 | 必填 | 枚举值 |
|---|---|---|---|---|
| text | Text to synthesize (max 15,000 characters). Supports inline speech tags such as [pause], [laugh], and wrapping tags like |
string | 是 | - |
| language | BCP-47 language code, or auto for automatic detection. | string | 是 | auto, en, ar-EG, ar-SA, ar-AE, bn, zh, fr, de, hi, id, it, ja, ko, pt-BR, pt-PT, ru, es-MX, es-ES, tr, vi |
| voice_id | Voice ID for synthesis. Built-in voices are listed below (26 total, case-insensitive). Custom voice IDs from your xAI voice library are also accepted. | string | 否 | - |
| bit_rate | MP3 bit rate in bps. Only applied when codec is mp3. Default 128000. | integer | 否 | 32000, 64000, 96000, 128000, 192000 |
| codec | Audio codec. Default mp3. | string | 否 | mp3, wav, pcm, mulaw, alaw |
| optimize_streaming_latency | Latency vs quality trade-off: 0 best quality (default), 1 lower first-byte latency, 2 lowest first-byte latency. | integer | 否 | 0, 1, 2 |
| sample_rate | Sample rate in Hz. Default 24000. | integer | 否 | 8000, 16000, 22050, 24000, 44100, 48000 |
| speed | Speech speed multiplier. Range 0.7–1.5. Default 1.0. | number | 否 | - |
| text_normalization | When true, normalize written-form text (numbers, abbreviations) before synthesis. | boolean | 否 | true, false |
价格
输入图片（$/img）: 0.0000
输入视频（$/sec）: 0.0000
单位: $/M chars
| 价格 |
|---|
| $15.0000/M chars |
相关模型
- xai/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.
