SaynaAI/sayna
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks
Rust-based real-time voice server with WebSocket/REST APIs supporting multiple STT/TTS providers (Deepgram, ElevenLabs, Google Cloud, Azure). Features include Silero-VAD with ML-based turn detection, optional DeepFilterNet noise filtering, LiveKit WebRTC integration, and pluggable provider architecture. Offers audio-disabled development mode and optional external authentication via RSA token validation.
158 stars.
Stars
158
Forks
26
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/SaynaAI/sayna"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
bolna-ai/bolna
Conversational voice AI agents
MCERQUA/OpenVoiceUI
Open voice UI shell for AI agents. Bring any LLM, TTS, or framework — handles voice I/O, Agent...
HaoZhang615/Realtime-Synthetic-Call-Center-Agents
a solution that simulates AI-driven contact center scenarios using synthetic data and real-time...
jesuscopado/samantha-os1-openai-realtime
Samantha OS1 is a conversational AI assistant powered by the Realtime API from OpenAI
ShaerWare/AI_Secretary_System
📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2,...