> ## 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 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. ## OpenAPI ````yaml /model-api/xai/xai-tts.json post /xai/grok-voice-tts openapi: 3.1.0 info: title: xAI Grok Voice Text-to-Speech API description: >- xAI Grok Voice text-to-speech. Submit text as an async task; poll GET /api/v1/tasks/{task_id} for the synthesized audio. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: xAI Grok Voice text-to-speech models API security: - bearerAuth: [] paths: /xai/grok-voice-tts: post: summary: Grok Voice TTS description: >- [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. operationId: grokVoiceTTS requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GrokVoiceTTSRequest' examples: basic: summary: Minimal request (default voice eve) value: text: Hello! Welcome to the xAI Text to Speech API. language: en builtin_voice_ara: summary: Built-in voice ara value: text: Hello from Ara. language: en voice_id: ara full_options: summary: Full options value: text: Crystal clear audio at maximum quality. language: en voice_id: rex codec: mp3 sample_rate: 44100 bit_rate: 192000 speed: 1.2 text_normalization: true optimize_streaming_latency: 0 responses: '200': description: >- Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio 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-tts-001 model_id: xai/grok-voice-tts get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-grok-voice-tts-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: GrokVoiceTTSRequest: type: object required: - text - language additionalProperties: false properties: text: type: string minLength: 1 maxLength: 15000 description: >- Text to synthesize (max 15,000 characters). Supports inline speech tags such as [pause], [laugh], and wrapping tags like .... language: type: string enum: - 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 description: BCP-47 language code, or auto for automatic detection. voice_id: default: eve description: >- 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. anyOf: - type: string enum: - 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 description: 'Built-in voices (26). Default: eve.' - type: string minLength: 1 description: Custom voice ID from your xAI voice library. codec: type: string enum: - mp3 - wav - pcm - mulaw - alaw default: mp3 description: Audio codec. Default mp3. sample_rate: type: integer enum: - 8000 - 16000 - 22050 - 24000 - 44100 - 48000 default: 24000 description: Sample rate in Hz. Default 24000. bit_rate: type: integer enum: - 32000 - 64000 - 96000 - 128000 - 192000 default: 128000 description: MP3 bit rate in bps. Only applied when codec is mp3. Default 128000. speed: type: number minimum: 0.7 maximum: 1.5 default: 1 description: Speech speed multiplier. Range 0.7–1.5. Default 1.0. text_normalization: type: boolean default: false description: >- When true, normalize written-form text (numbers, abbreviations) before synthesis. optimize_streaming_latency: type: integer enum: - 0 - 1 - 2 default: 0 description: >- Latency vs quality trade-off: 0 best quality (default), 1 lower first-byte latency, 2 lowest first-byte latency. 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; audio appears in result.resources. 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-tts-001 model_id: type: string description: Model ID in provider/model format example: xai/grok-voice-tts 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-tts-001 responses: BadRequest: description: Bad request Unauthorized: description: Unauthorized TooManyRequests: description: Rate limited InternalServerError: description: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer ````