{"servers":[{"url":"https://api.modellix.ai/api/v1/minimax/minimax-voice-clone"}],"post":{"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":{"content":{"application/json":{"examples":{"basic":{"summary":"Minimal clone + TTS","value":{"audio_url":"https://example.com/reference.wav","model":"speech-2.8-turbo","text":"Welcome to Modellix speech synthesis."}},"with_clone_prompt":{"summary":"Optional short prompt_audio to stabilize clone","value":{"audio_url":"https://example.com/reference.wav","language_boost":"English","model":"speech-2.8-hd","prompt_audio":"https://example.com/short-sample.wav","prompt_text":"Short sample content.","text":"This is the longer text for final synthesis."}},"with_controls":{"summary":"With language boost and prosody","value":{"audio_url":"https://example.com/reference.wav","format":"mp3","language_boost":"English","model":"speech-2.8-hd","need_noise_reduction":false,"pitch":0,"sample_rate":32000,"speed":1,"text":"There is a large garden behind my house.","vol":1}}},"schema":{"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":{"aigc_watermark":{"default":false,"description":"Whether to append an AIGC watermark to the returned audio. Default false.","example":false,"type":"boolean"},"audio_url":{"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.","example":"https://example.com/reference.wav","maxLength":2048,"minLength":1,"type":"string"},"bitrate":{"default":128000,"description":"Audio bitrate. Default 128000. Only effective when format is mp3; ignored for other formats.","enum":[32000,64000,128000,256000],"example":128000,"type":"integer"},"channel":{"default":1,"description":"Output channel count. 1 is mono, 2 is stereo. Default 1.","enum":[1,2],"example":1,"type":"integer"},"emotion":{"description":"Optional emotion control. Leave unset to let the model infer from text.","enum":["happy","sad","angry","fearful","disgusted","surprised","calm"],"example":"happy","type":"string"},"force_cbr":{"default":false,"description":"Force constant bitrate encoding. Optional; typically unused for standard async synthesis. Default false.","example":false,"type":"boolean"},"format":{"default":"mp3","description":"Output audio encoding format. Default mp3. Result audio is returned as a URL on the completed task.","enum":["mp3","pcm","flac","wav"],"example":"mp3","type":"string"},"language_boost":{"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","type":"string"},"latex_read":{"default":false,"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.","example":false,"type":"boolean"},"model":{"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","type":"string"},"modify_intensity":{"description":"Voice effect intensity: lower is stronger, higher is softer. Range [-100, 100].","example":0,"maximum":100,"minimum":-100,"type":"integer"},"modify_pitch":{"description":"Voice effect pitch: lower is deeper, higher is brighter. Range [-100, 100]. Distinct from pitch (semitone).","example":0,"maximum":100,"minimum":-100,"type":"integer"},"modify_timbre":{"description":"Voice effect timbre: lower is thicker, higher is brighter or crisper. Range [-100, 100].","example":0,"maximum":100,"minimum":-100,"type":"integer"},"need_noise_reduction":{"default":false,"description":"Whether to enable noise reduction on the clone reference audio. Default false.","example":false,"type":"boolean"},"need_volume_normalization":{"default":false,"description":"Whether to enable volume normalization for cloning. Default false.","example":false,"type":"boolean"},"pitch":{"default":0,"description":"Pitch adjustment in semitones. Default 0. Range [-12, 12]. Distinct from modify_pitch (voice effect).","example":0,"maximum":12,"minimum":-12,"type":"integer"},"prompt_audio":{"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.","example":"https://example.com/short-sample.wav","maxLength":2048,"minLength":1,"type":"string"},"prompt_text":{"description":"Optional transcript matching prompt_audio. Must align with the example audio content; end with punctuation. Not a substitute for text.","example":"Short sample content.","maxLength":1000,"minLength":1,"type":"string"},"pronunciation_tone":{"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\"].","example":["omg/oh my god"],"items":{"type":"string"},"type":"array"},"sample_rate":{"default":32000,"description":"Output sample rate in Hz. Default 32000.","enum":[8000,16000,22050,24000,32000,44100],"example":32000,"type":"integer"},"sound_effects":{"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","type":"string"},"speed":{"default":1,"description":"Speech rate multiplier for synthesis. Default 1.0. Range [0.5, 2.0].","example":1,"maximum":2,"minimum":0.5,"type":"number"},"subtitle_enable":{"default":false,"description":"Whether to generate a subtitle download link. Default false.","example":false,"type":"boolean"},"text":{"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).","example":"Welcome to Modellix speech synthesis.","maxLength":9999,"minLength":1,"type":"string"},"text_normalization":{"default":false,"description":"Enable Chinese/English text normalization for better number reading; may add slight latency. Default false.","example":false,"type":"boolean"},"vol":{"default":1,"description":"Speech volume for synthesis. Default 1.0. Range (0.0, 10.0].","example":1,"exclusiveMinimum":0,"maximum":10,"type":"number"}},"required":["model","audio_url","text"],"type":"object"}}},"required":true},"responses":{"200":{"content":{"application/json":{"example":{"code":0,"data":{"get_result":{"method":"GET","url":"https://api.modellix.ai/api/v1/tasks/task-minimax-voice-clone-001"},"model_id":"minimax/minimax-voice-clone","status":"pending","task_id":"task-minimax-voice-clone-001"},"message":"success"},"schema":{"description":"Response object for asynchronous task submission.","properties":{"code":{"description":"Response code, 0 indicates success","example":0,"type":"integer"},"data":{"description":"Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; audio appears in result.resources.","properties":{"get_result":{"description":"Endpoint to query the task result. See Common API: Query Task Result.","properties":{"method":{"example":"GET","type":"string"},"url":{"example":"https://api.modellix.ai/api/v1/tasks/task-minimax-voice-clone-001","type":"string"}},"type":"object"},"model_id":{"description":"Model ID in provider/model format","example":"minimax/minimax-voice-clone","type":"string"},"status":{"description":"Initial task status","enum":["pending","processing"],"example":"pending","type":"string"},"task_id":{"description":"Unique task identifier for polling","example":"task-minimax-voice-clone-001","type":"string"}},"required":["status","task_id","model_id"],"type":"object"},"message":{"description":"Response message","example":"success","type":"string"}},"required":["code","message","data"],"type":"object"}}},"description":"Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result."},"400":{"content":{"application/json":{"schema":{"properties":{"code":{"example":400,"type":"integer"},"message":{"example":"Invalid parameters: model is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Invalid request parameters"},"401":{"content":{"application/json":{"schema":{"properties":{"code":{"example":400,"type":"integer"},"message":{"example":"Invalid parameters: model is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Unauthorized - Invalid or missing API Key"},"429":{"content":{"application/json":{"schema":{"properties":{"code":{"example":400,"type":"integer"},"message":{"example":"Invalid parameters: model is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Rate limit exceeded"},"500":{"content":{"application/json":{"schema":{"properties":{"code":{"example":400,"type":"integer"},"message":{"example":"Invalid parameters: model is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Internal server error"}},"summary":"MiniMax One-shot Voice Clone + TTS","x-mint":{"href":"minimax/minimax-voice-clone"}}}