LaunchDevelopersAugust 1, 2026
audio.cpp 0.5 adds DramaBox expressive TTS, Confucius4 and 7 more models

Release 0.5 ships 9 new TTS models led by DramaBox, a prompt-directed voice-acting model built on the LTX-2.3 audio architecture, plus Confucius4 cross-lingual voice transfer and ROCm/HIP support. Prompts can control emotion, delivery, laughs, sighs, pauses, and speaker behavior.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Developer claims Claude Code now handles 95% of his work
- Semantica provides open-source enterprise intelligence layer for AI agents
- Best practices for creating professional-grade agent skills
- Bloomberg video explores Africa's role in AI infrastructure
- Creative Intelligence Suite provides agents for structured ideation