Source
CosyVoice official model/project documentation
Read the primary source.
Reference illustration, not a screenshot of this source.
CosyVoice
Speech engine or client · Voice
Multilingual speech-generation family with inference and deployment tooling.
Use it for
Choose when you need a controllable multilingual model route in an application you can operate.
Choose something else for
Not a complete voice studio or conversational system.
Give it
Text; Reference audio where supported
Get back
Speech audio
How it is operated
Engine/client, often exposed through voice-pro
Availability
Provider capabilities and historical Studio notes are distinguished below. Current account access, credits and runtime readiness were not tested.
How charging works
Compute and model/weight terms; hosted wrappers charge separately.
Where processing happens
Self-hosted if deployed locally, otherwise provider-dependent.
Language support
Exact model version determines support.
Choose an underlying speech engine
★★★★☆ 4/5 for this task
Editorial task fit based on the documented role and integration requirements. Pin the version and test the intended language, reference voice and streaming mode.
Decision: Choose when you need a controllable multilingual model route in an application you can operate.
Limits and things to check
- Pin the version and test the intended language, reference voice and streaming mode.
Pin the version and test the intended language, reference voice and streaming mode.
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.
