Coming Soon
We are actively developing the following features and expect to launch them publicly soon.Avatar Enhancements
- Self-service avatar creation from videos, single images, and prompts
- Controllable avatar emotions (neutral, happy, sad, angry, …)
- Avatar active listening behavior (nodding when listening to user)
- Improved body and head movements for enhanced hyper-realism
- Increase stock avatar variety, diversity, quality, and polish
- Hidden machine-readable watermarking (following EU AI Act Art. 50.2)
Managed Agents
- Enhanced multilingual support (multiple languages per conversation)
- Function calling capabilities with declarative tool access
- Meeting tool integration support (Teams, Zoom, …)
- TTS model selection and voice selection
- TTS pronunciation dictionary support
- Customization options for noise cancellation, voice isolation, interruption handling, turn-taking, and inactive user management
- Improving vision mode to no longer affect response latency
Speech-to-Video API
- Optimizing initial avatar loading speed
Studio
- Self-service avatar creation from videos, single images, and prompts
- Multi-factor authentication support
- Workspace support (e.g. to support dev/prod environments)
Planned Features
The following features are planned but do not have a concrete launch plan yet. If you need one of these urgently, contact support and we may prioritize it earlier for you.Avatar Enhancements
- Controllable gestures (waving, nodding, …)
- Controllable eye gaze
- Improved facial hair rendering
- Customizable avatar backgrounds
- On-device rendering support
- Faster avatar creation
- Hair and clothing customization
Managed Agents
- Custom TTS integrations
- TTS custom voice cloning support
- Document / presentation sharing
- Persistent conversation histories across conversations
- Support for storing audio and video recordings of conversations
- Web search support
- Website knowledge base support
Speech-to-Video API
- MCP server for AI coding support
- Raw WebRTC / framework-agnostic Speech-to-Video API
- Pipecat integration support for Genesis-2 model
- Cognigy integration support
- Agora integration support
- VideoSDK integration support
Studio
- Speech-to-Video video rendering support
- Extended usage analytics with session statistics, end-user distributions, and latency/performance metrics by service
- Zero data retention toggle (already available upon request)
- Single sign-on support