qwen-tts-voice-enrollment

Registers a cloned voice on Alibaba Cloud Model Studio from a reference recording the user is authorized to use, enrolling it against one Qwen TTS voice-clone model string, then synthesizing speech from text with the returned voice ID under that same model. Covers consent capture, model binding, and separate human approvals for enrollment, billable synthesis, streamed or signed-URL audio receipt, retention, download, deletion of retained clips, and voice removal. Use when a user with documented rights to a recording asks to enroll that voice for text to speech and reuse it with the same model. Not for designing synthetic voices with no source recording, everyday preset-voice realtime synthesis, or any cloning that lacks explicit consent.

Version

v1.0.0

Size

16 KB

Updated

2026-10-10

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.