Key Info
Tencent has reportedly released a new AI model that can edit audio content, voice and emotional tone from a single instruction, letting the same words be delivered in a completely different way.
Highlights
- The model focuses on audio-level editing: one instruction can change the actual content, the speaker's voice, and the emotional delivery.
- Tencent AI's official newsroom amplified the announcement via retweet; the post does not yet name the model or provide technical details.