Running
MOSS Voice-Acting — Turning the Emotion Up at Inference Time
🔊
Adjust emotional tone in generated speech
open multi-modal foundation models and datasets for their creation; scaling laws, model evaluation; fully local, sovereign model deployment, personalized assistants and open local agentic systems
Adjust emotional tone in generated speech
A controlled 4-factor study on the MOSS voice-acting model
Generate expressive speech from stage directions
Listen to emotion‑controlled speech samples
Explore and compare voice‑acting model performance with audio samples
Generate emotional voice clips with precise timing
Generate emotion‑controlled speech from timed scripts
Listen to and compare voice‑acting model samples
Generate descriptive captions for images using advanced AI technology