Qwen3 TTS Prompting

Choose mode

CustomVoice

Use a supported predefined speaker plus optional natural-language instruct control for delivery.

Required fields: text, language, speaker. Optional: instruct.

VoiceDesign

Use the 1.7B VoiceDesign model to create a new voice from a natural-language description.

Required fields: text, language, instruct.

The instruction should describe audible traits such as approximate vocal age, register, timbre, cadence, articulation, breath, accent only when decided, and delivery behavior. Avoid visual personality traits that cannot be heard.

VoiceClone