Design a Voice

Describe a voice in words and let the AI create it. No recording needed.

Voice Design samples Preview a sample or use it to fill the editor below.
Name
Sex
Language
Description
Sample text
Actions

Describe the voice

Describe the voice you want. Qwen3-TTS VoiceDesign will synthesise it from the description and sample text.

DimensionExamples
GenderMale, female, neutral
AgeChild (5-12), teenager (13-18), young adult (19-35), middle-aged (36-55), elderly (55+)
PitchHigh, mid, low, slightly high, slightly low
Speaking rateFast, moderate, slow, slightly fast, slightly slow
EmotionCheerful, calm, gentle, serious, lively, composed, soothing
CharacteristicsMagnetic, crisp, husky, smooth, sweet, rich, powerful
Use caseNews broadcasting, advertisement voice-over, audiobook, animated character, voice assistant, documentary narration

Reference transcript & generate

This shared reference transcript is used by samples, prompt presets, generation, preview, download, and export to the Voice Clone Library.

Voice Design prompt library

Save, load, and delete named voice description presets for quick reuse.

Custom Voice (Qwen style control)

CustomVoice uses Qwen's configured premium/custom speakers. It is the best place to test style instructions when you can use one of the CustomVoice timbres.

Best for style control over configured target timbres.
model voice style-aware stream-capable model
It does not automatically reuse arbitrary WAV voices from the Voice Clone library. For your own recurring character, create/fine-tune/configure that voice here, or design/export a WAV and then clone it.