Source
Qwen3-TTS official model/project documentation
Read the primary source.
Reference illustration, not a screenshot of this source.
Qwen3-TTS
Speech-generation engine · Voice
Speech generation family with separate voice-design, custom-voice and cloning models.
Use it for
Choose when you need instruction-led voice design or a supported cloning route.
Choose something else for
Do not treat a model listing as installed and ready.
Give it
Text; Reference audio where supported
Get back
Speech audio
How it is operated
Model runtime or compatible application
Availability
Provider capabilities and historical Studio notes are distinguished below. Current account access, credits and runtime readiness were not tested.
How charging works
Model compute; deployment or hosted-service charges.
Where processing happens
Local/self-hosted, or selected cloud provider.
Language support
Official series includes English, French, Spanish and other named languages; model variant matters.
Choose an underlying speech engine
★★★★☆ 4/5 for this task
Editorial task fit based on the documented role and integration requirements. VoiceDesign, CustomVoice and Base are different models. Pick the correct one; advertised cloning input length is not an output-quality guarantee.
Decision: Choose when you need instruction-led voice design or a supported cloning route.
Limits and things to check
- VoiceDesign, CustomVoice and Base are different models. Pick the correct one; advertised cloning input length is not an output-quality guarantee.
VoiceDesign, CustomVoice and Base are different models. Pick the correct one; advertised cloning input length is not an output-quality guarantee.
Evidence
Official model/project documentation reviewed; no same-script listening test
Catalogue review: 2026-09-05. The evidence note identifies what was verified. This date does not imply a fresh tool test or verification of every linked source.
