> ## 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. # MiniMax One-shot Voice Clone + TTS > [Core Function] MiniMax Voice Clone clones a speaker from a public reference audio URL and synthesizes new speech in one async request; only the final audio is returned. [Strengths] No voice enrollment management; optional language_boost for clone and synthesis; prosody controls (speed, volume, pitch, emotion); pronunciation overrides; voice effects; flexible audio formats. [Best For] One-off cloned narration, personalized prompts, and demos where a lasting voice library is not needed. [Limitations] Do NOT use this to obtain a reusable voice library entry; the cloned voice is temporary and is not returned. audio_url must be publicly reachable (mp3/m4a/wav, 10s–5min, ≤20 MB). [Routing] Choose speech-2.8-hd for higher quality; speech-2.8-turbo for lower latency or cost. Paralinguistic tags such as (laughs) in text are supported on both speech-2.8-hd and speech-2.8-turbo. ## OpenAPI ````yaml /model-api/minimax/minimax-s2s.json post /minimax/minimax-voice-clone openapi: 3.1.0 info: title: MiniMax Voice Clone API description: >- MiniMax one-shot voice cloning and speech synthesis. Submit a public reference audio URL with text as an async task; poll GET /api/v1/tasks/{task_id} for the synthesized audio. The cloned voice is temporary and is not returned to the client. Supported speech models: speech-2.8-hd, speech-2.8-turbo. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: Modellix API security: - bearerAuth: [] paths: /minimax/minimax-voice-clone: post: summary: MiniMax One-shot Voice Clone + TTS description: >- [Core Function] MiniMax Voice Clone clones a speaker from a public reference audio URL and synthesizes new speech in one async request; only the final audio is returned. [Strengths] No voice enrollment management; optional language_boost for clone and synthesis; prosody controls (speed, volume, pitch, emotion); pronunciation overrides; voice effects; flexible audio formats. [Best For] One-off cloned narration, personalized prompts, and demos where a lasting voice library is not needed. [Limitations] Do NOT use this to obtain a reusable voice library entry; the cloned voice is temporary and is not returned. audio_url must be publicly reachable (mp3/m4a/wav, 10s–5min, ≤20 MB). [Routing] Choose speech-2.8-hd for higher quality; speech-2.8-turbo for lower latency or cost. Paralinguistic tags such as (laughs) in text are supported on both speech-2.8-hd and speech-2.8-turbo. operationId: minimaxVoiceClone requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/MiniMaxVoiceCloneRequest' examples: basic: summary: Minimal clone + TTS value: model: speech-2.8-turbo audio_url: https://example.com/reference.wav text: Welcome to Modellix speech synthesis. with_controls: summary: With language boost and prosody value: model: speech-2.8-hd audio_url: https://example.com/reference.wav text: There is a large garden behind my house. language_boost: English format: mp3 sample_rate: 32000 speed: 1 vol: 1 pitch: 0 need_noise_reduction: false with_clone_prompt: summary: Optional short prompt_audio to stabilize clone value: model: speech-2.8-hd audio_url: https://example.com/reference.wav text: This is the longer text for final synthesis. prompt_audio: https://example.com/short-sample.wav prompt_text: Short sample content. language_boost: English 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-minimax-voice-clone-001 model_id: minimax/minimax-voice-clone get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-minimax-voice-clone-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: MiniMaxVoiceCloneRequest: type: object required: - model - audio_url - text description: >- One-shot voice clone + TTS request. Required: model, audio_url, text. Optional: prompt_audio/prompt_text, clone processing, language_boost, AIGC watermark, TTS prosody/audio/pronunciation/voice effects, and subtitles. The cloned voice is temporary and is not returned. properties: model: $ref: '#/components/schemas/MiniMaxSpeechModel' audio_url: type: string description: >- Primary reference audio URL for cloning. Must be publicly accessible without auth. Formats: mp3, m4a, wav. Duration 10 seconds–5 minutes. File size ≤20 MB. Distinct from prompt_audio. minLength: 1 maxLength: 2048 example: https://example.com/reference.wav text: type: string description: >- Text to synthesize with the temporarily cloned voice. Required. Fewer than 10,000 Unicode characters. On speech-2.8-hd / speech-2.8-turbo, may include paralinguistic tags such as (laughs), (breath), or (sighs). minLength: 1 maxLength: 9999 example: Welcome to Modellix speech synthesis. prompt_audio: type: string description: >- Optional short example audio URL to improve clone similarity and stability. Not a substitute for audio_url. Formats: mp3, m4a, wav. Duration must be under 8 seconds. File size ≤20 MB. minLength: 1 maxLength: 2048 example: https://example.com/short-sample.wav prompt_text: type: string description: >- Optional transcript matching prompt_audio. Must align with the example audio content; end with punctuation. Not a substitute for text. minLength: 1 maxLength: 1000 example: Short sample content. need_noise_reduction: type: boolean description: >- Whether to enable noise reduction on the clone reference audio. Default false. default: false example: false need_volume_normalization: type: boolean description: Whether to enable volume normalization for cloning. Default false. default: false example: false language_boost: $ref: '#/components/schemas/MiniMaxLanguageBoost' aigc_watermark: type: boolean description: >- Whether to append an AIGC watermark to the returned audio. Default false. default: false example: false speed: type: number description: Speech rate multiplier for synthesis. Default 1.0. Range [0.5, 2.0]. minimum: 0.5 maximum: 2 default: 1 example: 1 vol: type: number description: Speech volume for synthesis. Default 1.0. Range (0.0, 10.0]. exclusiveMinimum: 0 maximum: 10 default: 1 example: 1 pitch: type: integer description: >- Pitch adjustment in semitones. Default 0. Range [-12, 12]. Distinct from modify_pitch (voice effect). minimum: -12 maximum: 12 default: 0 example: 0 emotion: type: string description: >- Optional emotion control. Leave unset to let the model infer from text. enum: - happy - sad - angry - fearful - disgusted - surprised - calm example: happy text_normalization: type: boolean description: >- Enable Chinese/English text normalization for better number reading; may add slight latency. Default false. default: false example: false latex_read: type: boolean description: >- Enable reading LaTeX formulas aloud (Chinese only). When true, language_boost may be forced to Chinese. Wrap formulas with $$ and escape backslashes. Default false. default: false example: false sample_rate: type: integer description: Output sample rate in Hz. Default 32000. enum: - 8000 - 16000 - 22050 - 24000 - 32000 - 44100 default: 32000 example: 32000 bitrate: type: integer description: >- Audio bitrate. Default 128000. Only effective when format is mp3; ignored for other formats. enum: - 32000 - 64000 - 128000 - 256000 default: 128000 example: 128000 format: type: string description: >- Output audio encoding format. Default mp3. Result audio is returned as a URL on the completed task. enum: - mp3 - pcm - flac - wav default: mp3 example: mp3 channel: type: integer description: Output channel count. 1 is mono, 2 is stereo. Default 1. enum: - 1 - 2 default: 1 example: 1 force_cbr: type: boolean description: >- Force constant bitrate encoding. Optional; typically unused for standard async synthesis. Default false. default: false example: false pronunciation_tone: type: array description: >- Custom pronunciation rules. Use / as separator. For Mandarin entries, tones are digits 1-5 (5=neutral), e.g. name/(yan4)(shao3)(fei1). Example: ["omg/oh my god"]. items: type: string example: - omg/oh my god modify_pitch: type: integer description: >- Voice effect pitch: lower is deeper, higher is brighter. Range [-100, 100]. Distinct from pitch (semitone). minimum: -100 maximum: 100 example: 0 modify_intensity: type: integer description: >- Voice effect intensity: lower is stronger, higher is softer. Range [-100, 100]. minimum: -100 maximum: 100 example: 0 modify_timbre: type: integer description: >- Voice effect timbre: lower is thicker, higher is brighter or crisper. Range [-100, 100]. minimum: -100 maximum: 100 example: 0 sound_effects: type: string description: >- Optional sound effect applied to the output. Supported for mp3, wav, and flac. enum: - spacious_echo - auditorium_echo - lofi_telephone - robotic example: spacious_echo subtitle_enable: type: boolean description: Whether to generate a subtitle download link. Default false. default: false example: false 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-minimax-voice-clone-001 model_id: type: string description: Model ID in provider/model format example: minimax/minimax-voice-clone 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-minimax-voice-clone-001 MiniMaxSpeechModel: type: string description: >- Supported MiniMax speech model for both voice clone and TTS in this request. enum: - speech-2.8-hd - speech-2.8-turbo example: speech-2.8-turbo MiniMaxLanguageBoost: type: string description: >- Optional language or dialect boost for both cloning and synthesis. Omit for default behavior. Use auto to let the model decide. enum: - Chinese - Chinese,Yue - English - Arabic - Russian - Spanish - French - Portuguese - German - Turkish - Dutch - Ukrainian - Vietnamese - Indonesian - Japanese - Italian - Korean - Thai - Polish - Romanian - Greek - Czech - Finnish - Hindi - Bulgarian - Danish - Hebrew - Malay - Persian - Slovak - Swedish - Croatian - Filipino - Hungarian - Norwegian - Slovenian - Catalan - Nynorsk - Tamil - Afrikaans - auto example: Chinese ErrorResponse: type: object required: - code - message properties: code: type: integer example: 400 message: type: string example: 'Invalid parameters: model is required' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' TooManyRequests: description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Modellix API Key. Format: Bearer ' ````