Resources
Changelog
Changes
- Added a new recording requirement to Replica Training: Start the talking segment with a big smile.
Enhancements
Changes
- Added a new recording requirement to Replica Training: Start the talking segment with a big smile.
Enhancements
Changes
- Added a new recording requirement to Replica Training: Start the talking segment with a big smile.
New Features
No features were added in this release.
Enhancements
- Major Phoenix 3 Enhancements for CVI:
- Increased frame rate from 27fps to 32fps, significantly boosting smoothness.
- Reduced Phoenix step’s warm boot time by 60% (from 5s to 2s).
- Lipsync accuracy improved by ~22% based on AVSR metric.
- Resolved blurriness and choppiness at conversation start.
- Enhanced listening mode with more natural micro expressions (eyebrow movements, subtle gestures).
- Greenscreen mode speed boosted by an additional ~1.5fps.
- Enhanced CVI Audio Quality: Audio clicks significantly attenuated, providing clearer conversational audio.
- Phoenix 3 Visual Artifacts Fix: Resolved visual artifacts in 4K videos on Apple devices, eliminating black spot artifacts in thumbnails.
New Features
No features were added in this release.
Enhancements
- Major Phoenix 3 Enhancements for CVI:
- Increased frame rate from 27fps to 32fps, significantly boosting smoothness.
- Reduced Phoenix step’s warm boot time by 60% (from 5s to 2s).
- Lipsync accuracy improved by ~22% based on AVSR metric.
- Resolved blurriness and choppiness at conversation start.
- Enhanced listening mode with more natural micro expressions (eyebrow movements, subtle gestures).
- Greenscreen mode speed boosted by an additional ~1.5fps.
- Enhanced CVI Audio Quality: Audio clicks significantly attenuated, providing clearer conversational audio.
- Phoenix 3 Visual Artifacts Fix: Resolved visual artifacts in 4K videos on Apple devices, eliminating black spot artifacts in thumbnails.
New Features
No features were added in this release.
Enhancements
- Faster Phoenix 3 Video Gen: Substantially lowered generation times
- 4K videos: reduced from ~22 mins to ~10 mins per minute generated.
- 1080p videos: down from ~8 mins to ~3.25 mins per minute generated.
New Features
- Launched LiveKit Integration: With Tavus video agents now integrated into LiveKit, you can add humanlike video responses to your voice agents in seconds.
- Persona API: Enabled patch updates to personas.
Enhancements
- Resolved TTS (Cartesia) stability issues and addressed hallucination.
- Phoenix 3 Improvements:
- Fixed blinking/jumping issues and black spots in videos.
- FPS optimization to resolve static and audio crackling.
New Features
- Launched LiveKit Integration: With Tavus video agents now integrated into LiveKit, you can add humanlike video responses to your voice agents in seconds.
- Persona API: Enabled patch updates to personas.
Enhancements
- Resolved TTS (Cartesia) stability issues and addressed hallucination.
- Phoenix 3 Improvements:
- Fixed blinking/jumping issues and black spots in videos.
- FPS optimization to resolve static and audio crackling.
New Features
No features were added in this release.
Enhancements
- Wave Feature Enhancements: Rolling out fixes for replicas previously missing wave/no-wave functionality.
New Features
No features were added in this release.
Enhancements
No enhancements were made in this release.
New Features
No features were added in this release.
Enhancements
No enhancements were made in this release.
New Features
- Added the
audio_urlparameter in the/videosendpoint to generate videos using any custom audio source.
Enhancements
No enhancements were made in this release.
New Features
No features were added in this release.
Enhancements
- Replica API:
- Enhanced Error Messaging for Training Videos.
- Optimized Auto QA for Training Videos.
New Features
No features were added in this release.
Enhancements
- Replica API:
- Enhanced Error Messaging for Training Videos.
- Optimized Auto QA for Training Videos.
New Features
No features were added in this release.
Enhancements
No enhancements were made in this release.