Qwen3-TTS-VC is Alibaba Tongyi's voice-cloning text-to-speech model — enroll a custom voice from a short reference clip, then synthesize any text in that voice across multiple languages.
# 1) clone a voice (returns a voice id)
curl https://conduit-api.bifrostapi.net/v1/audio/voices \
-H "Authorization: Bearer ck-YOUR_KEY" -F "file=@sample.wav"
# 2) speak with the cloned voice id
curl https://conduit-api.bifrostapi.net/v1/audio/speech \
-H "Authorization: Bearer ck-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3-tts-vc","input":"你好","voice":"<your-voice-id>"}' --output out.wav→ Clone a voice first, then pass its id to /audio/speech.
Auth, billing & streaming → Quickstart