{"servers":[{"url":"https://api.modellix.ai/api/v1/alibaba/cosyvoice-clone"}],"post":{"description":"[Core Function] CosyVoice 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; language_hint applies to both cloning and synthesis; SSML, hot_fix, and prosody controls. [Best For] One-off cloned narration 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. Reference URL must be publicly accessible. model must be cosyvoice-v3.5-plus or cosyvoice-v3.5-flash. [Routing] Choose cosyvoice-v3.5-plus for higher speech quality; cosyvoice-v3.5-flash for lower latency.","operationId":"cosyvoiceClone","requestBody":{"content":{"application/json":{"example":{"enable_preprocess":false,"format":"mp3","language_hint":"en","model":"cosyvoice-v3.5-plus","text":"There is a large garden behind my house.","url":"https://example.com/reference.wav"},"schema":{"description":"One-shot voice clone + TTS request. Required: model, url, text. The cloned voice is temporary and is not returned.","properties":{"bit_rate":{"description":"Audio bit rate in kbps. Optional. Range 6–510. Only supported when format is opus; do not send for mp3, pcm, or wav.","example":32,"maximum":510,"minimum":6,"type":"integer"},"enable_preprocess":{"default":false,"description":"Enable noise reduction and audio enhancement before cloning. Default false.","example":false,"type":"boolean"},"enable_ssml":{"default":false,"description":"Whether to parse text as SSML. Default false. When true, text must follow Alibaba CosyVoice SSML rules.","example":false,"type":"boolean"},"format":{"default":"mp3","description":"Output audio encoding format. Default mp3.","enum":["mp3","pcm","wav","opus"],"example":"mp3","type":"string"},"hot_fix":{"description":"Text hot-fix before synthesis. Optional object with pronunciation (custom pinyin) and replace (text substitution) arrays, per Alibaba CosyVoice HTTP API.","example":{"replace":[{"Modellix":"Modelix"}]},"type":"object"},"instruction":{"description":"Optional speaking-style instruction. Weighted length ≤100 (CJK ideographs count as 2).","example":"Speak in a friendly customer-service tone.","type":"string"},"language_hint":{"default":"zh","description":"Language hint for both cloning and synthesis. Default zh.","enum":["zh","en","fr","de","ja","ko","ru","pt","th","id","vi"],"example":"en","type":"string"},"max_prompt_audio_length":{"default":10,"description":"Max reference audio duration in seconds used for cloning (3.0–30.0). Default 10.0.","example":10,"maximum":30,"minimum":3,"type":"number"},"model":{"description":"Target CosyVoice v3.5 TTS model used for synthesis after cloning.","enum":["cosyvoice-v3.5-plus","cosyvoice-v3.5-flash"],"type":"string"},"pitch":{"default":1,"description":"Pitch multiplier. Default 1.0. Range 0.5–2.0.","example":1,"maximum":2,"minimum":0.5,"type":"number"},"rate":{"default":1,"description":"Speech rate multiplier. Default 1.0. Range 0.5–2.0.","example":1,"maximum":2,"minimum":0.5,"type":"number"},"sample_rate":{"default":22050,"description":"Output sample rate in Hz. Default 22050.","enum":[8000,16000,22050,24000,44100,48000],"example":24000,"type":"integer"},"seed":{"default":0,"description":"Random seed. Default 0. Range 0–65535.","example":0,"maximum":65535,"minimum":0,"type":"integer"},"text":{"description":"Text to synthesize with the temporarily cloned voice. Required. Max 20,000 Unicode characters. Supports plain text and SSML (set enable_ssml to true).","example":"There is a large garden behind my house.","maxLength":20000,"minLength":1,"type":"string"},"url":{"description":"Publicly accessible reference audio URL for cloning.","example":"https://example.com/reference.wav","maxLength":2048,"minLength":1,"type":"string"},"volume":{"default":50,"description":"Output volume. Default 50. Range 0–100.","example":50,"maximum":100,"minimum":0,"type":"integer"}},"required":["model","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-cosyvoice-clone-001"},"model_id":"alibaba/cosyvoice-clone","status":"pending","task_id":"task-cosyvoice-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-cosyvoice-clone-001","type":"string"}},"type":"object"},"model_id":{"description":"Model ID in provider/model format","example":"alibaba/cosyvoice-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-cosyvoice-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":"CosyVoice One-shot Voice Clone + TTS","x-mint":{"href":"alibaba/cosyvoice-clone"}}}