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.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Text to synthesize (max 15,000 characters). Supports inline speech tags such as [pause], [laugh], and wrapping tags like ....
1 - 15000BCP-47 language code, or auto for automatic detection.
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 for synthesis. Built-in voices are listed below (26 total, case-insensitive). Custom voice IDs from your xAI voice library are also accepted.
eve, ara, leo, rex, sal, altair, atlas, carina, castor, celeste, cosmo, helios, helix, iris, kepler, lumen, luna, lux, naksh, orion, perseus, rigel, sirius, ursa, zagan, zenith Audio codec. Default mp3.
mp3, wav, pcm, mulaw, alaw Sample rate in Hz. Default 24000.
8000, 16000, 22050, 24000, 44100, 48000 MP3 bit rate in bps. Only applied when codec is mp3. Default 128000.
32000, 64000, 96000, 128000, 192000 Speech speed multiplier. Range 0.7–1.5. Default 1.0.
0.7 <= x <= 1.5When true, normalize written-form text (numbers, abbreviations) before synthesis.
Latency vs quality trade-off: 0 best quality (default), 1 lower first-byte latency, 2 lowest first-byte latency.
0, 1, 2 Response
Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result.
Response object for asynchronous task submission.