[ STACK LIBRARY ]

Sayna

Sayna

Visit website

Speech-to-Text

ABOUT

Unified voice layer for AI agents delivering real-time speech-to-text and text-to-speech over WebSocket and REST.

Sayna builds a high-performance real-time voice processing server in Rust for AI agents. It provides unified speech-to-text and text-to-speech through WebSocket streaming and REST APIs, with VAD, turn detection, and noise filtering built in. The pluggable architecture supports Deepgram, ElevenLabs, Google Cloud, Azure, and Cartesia, and LiveKit integration enables WebRTC audio streaming. Developers run it via Docker with an official Python SDK available.

STACK COVERAGE

Speech-to-Text

Unified STT/TTS voice layer, SIP server, Voice analytics

DETAILS

FOUNDED

2025

DEPLOYMENT

Self-hosted

PRICING MODEL

Open source

Is this your company? To claim this listing or update its details, contact us at sunil@uniocommunity.com

UNIOVOICE AI STACK LIBRARY
Sayna logo
Trusted by Unio

Sayna

Speech-to-Text

Unified voice layer for AI agents delivering real-time speech-to-text and text-to-speech over WebSocket and REST.

UnifiedSTT/TTSvoicelayer,SIPserver,Voiceanalytics
Layer
Speech-to-Text
Market
Global
Founded
2025
Deployment
Self-hosted
Pricing
Open source
Listed on the Unio Voice AI Stack Library

More in this layer

var(--variable-H7lUBNgYB)

SpeechRouter

Speech-to-Text

Unified speech-to-text gateway that routes one API across 17-plus providers with mid-stream failover.

var(--variable-H7lUBNgYB)

3Play Media

Speech-to-Text

Video accessibility and localization platform that combines AI with human review for captions, audio description, subtitles and dubbing.

var(--variable-H7lUBNgYB)

AI-coustics

Speech-to-Text

Real-time speech enhancement that cleans audio so voice AI transcribes and responds reliably.