SaynaAI/sayna
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks
This project provides a unified voice interface for AI agents, allowing them to understand spoken language and respond with synthesized speech. It takes audio input and converts it to text, or takes text and converts it to natural-sounding speech, supporting various providers like Deepgram, ElevenLabs, Google Cloud, and Microsoft Azure. This tool is designed for developers building conversational AI applications, voicebots, or any system requiring real-time spoken interaction.
158 stars.
Use this if you are developing an AI agent or application that needs to interact with users via real-time speech, seamlessly switching between different voice AI providers, and require features like noise filtering or voice activity detection.
Not ideal if you only need basic, offline text-to-speech or speech-to-text functionality without the need for real-time processing, multiple provider integration, or advanced audio features.
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...
jesuscopado/samantha-os1-openai-realtime
Samantha OS1 is a conversational AI assistant powered by the Realtime API from OpenAI
Anil-matcha/AI-Voice-Agent
Self-hosted AI voice agent
HaoZhang615/Realtime-Synthetic-Call-Center-Agents
a solution that simulates AI-driven contact center scenarios using synthetic data and real-time...