CosyVoice One-shot Voice Design + TTS
[Core Function] CosyVoice Design creates a temporary voice from a natural-language voice_prompt and synthesizes speech in one async request; only the final audio is returned. [Strengths] No voice enrollment management; language_hint (zh/en) applies to both design and synthesis; same prosody and format controls as CosyVoice TTS. [Best For] One-off designed speech without storing enrolled voices. [Limitations] Do NOT use this to obtain a reusable voice library entry; the designed voice is temporary and is not returned. model must be cosyvoice-v3.5-plus or cosyvoice-v3.5-flash; voice_prompt and text are required.
Authorizations
Modellix API Key. Format: Bearer <your_api_key>
Body
One-shot voice design + TTS. Required: model, voice_prompt, text. The designed voice is temporary and is not returned.
Target CosyVoice v3.5 TTS model used for synthesis after voice design.
cosyvoice-v3.5-plus, cosyvoice-v3.5-flash Natural-language voice description (Chinese or English). Required. Max 500 Unicode characters.
1 - 500"Calm male announcer with a deep tone"
Text to synthesize with the temporarily designed voice. Required. Max 20,000 Unicode characters.
1 - 20000"Hello, welcome to Modellix. Today we will introduce our products."
Language hint for both design and synthesis (zh/en only). Default zh.
zh, en "en"
Output audio encoding format. Default mp3.
mp3, pcm, wav, opus "mp3"
Output sample rate in Hz. Default 22050.
8000, 16000, 22050, 24000, 44100, 48000 24000
Output volume. Default 50. Range 0–100.
0 <= x <= 10050
Speech rate multiplier. Default 1.0. Range 0.5–2.0.
0.5 <= x <= 21
Pitch multiplier. Default 1.0. Range 0.5–2.0.
0.5 <= x <= 21
Audio bit rate in kbps. Optional. Range 6–510. Only supported when format is opus.
6 <= x <= 51032
Optional speaking-style instruction. Weighted length ≤100 (CJK ideographs count as 2).
"Speak in a friendly customer-service tone."
Random seed. Default 0. Range 0–65535.
0 <= x <= 655350
Whether to parse text as SSML. Default false.
false
Text hot-fix before synthesis. Same as CosyVoice TTS hot_fix.
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.