Expired50% confidenceEventExact time
CosyVoice v3.5 was tested by creator PoWang as a potentially more stable alternative to Doubao TTS for AI voice acting
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
CosyVoice v3.5 in Practice: Solving the Performance Direction Challenge in AI Voice Acting
bilibili破妄-胖6/15/2026
Related Claims
UnverifiedCosyVoice v3.5 Plus supports free-form voice instruction control but does not support system-preset voice profiles, requiring users to design voices themselves68% similarPartially VerifiedCosyVoice is an open-source speech synthesis model from Alibaba's Tongyi Lab that supports zero-shot voice cloning and can generate a target voice timbre using just a few seconds of reference audio.68% similarUnverifiedCosyVoice v3.5 supports a voice design feature that allows users to generate entirely new timbres through natural language descriptions without providing reference audio.64% similarUnverifiedIn the 3D flight racing game development test, M2.5 used the Web Audio API's OscillatorNode to dynamically synthesize sound effects rather than loading external audio files.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/45638API
curl https://kongchang.com/api/v1/knowledge/claims/45638MCP
get_claim(id=45638)