Unverified50% confidenceFactExact time
In v3.32.0 the API adds prompt-based voice creation capability (PR #4091), enabling developers to generate custom voices through text descriptions without relying on a preset voice list.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
Unverifiedv3.24.0 adds support at the API level for custom voice creation and agent session events (PR #4013).79% similarUnverifiedVersion v3.26.1 fixes an issue with custom voice creation parameters, corresponding to PR #4038.73% similarUnverifiedWhen the developer added the voice layer to the agent, the model, instructions, and permissions all remained unchanged — only the format was switched to text in, audio out.72% similarUnverifiedThe plugin includes Tongyi Qianwen's text-to-speech node, voice design node, and voice cloning node, with the voice cloning node capable of automatically downloading models.72% similarUnverifiedCodec-based approaches (such as VALL-E and SoundStorm) encode speech into discrete tokens and then generate output using a language model approach, achieving better zero-shot voice cloning results.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049072API
curl https://kongchang.com/api/v1/knowledge/claims/1049072MCP
get_claim(id=1049072)