Sayna
Sayna is a self-hosted real-time voice server that provides speech-to-text and text-to-speech through WebSocket and REST APIs, with provider integrations, LiveKit streaming, and SIP telephony.
Where it fits
Sayna is listed in Real-Time, Development Frameworks. Use its original project documentation to confirm the features and setup for your intended workflow.
Explore components for interactive audio, video or other time-sensitive agent experiences. Evaluate interruption handling and end-to-end latency with the devices and network conditions your users have.
Before you choose
Use these category-level questions when reviewing this resource. They do not assert that this project supports a particular feature.
- What delay is acceptable for the actual conversation?
- Can a person interrupt the agent?
- How does the session recover from a connection failure?
Sources & project links
About this listing
Imported directory snapshot · 2026-10-26. The description and classification come from the earlier directory, adapted from awesome-ai-agents; current project behavior has not been independently tested.
Pricing, licensing, supported models and hosting requirements may change. Check the original project before installing or paying. Inclusion is not an endorsement or a performance rating.
Historical repository popularity
The old directory displayed 314 GitHub stars. Its original observation date is unknown. This is retained as historical context, not a live count or quality score.