rse/speechflow
Speech Processing Flow Graph
Builds directed acyclic graphs of modular processing nodes—combining local audio/text operations (noise suppression, VAD, pitch shifting) with cloud APIs (OpenAI, Deepgram, ElevenLabs, DeepL) and network transports (WebSocket, MQTT, WebRTC)—enabling complex pipelines like real-time speech-to-text-to-speech translation. Written in TypeScript/Node.js with a declarative DSL for composing nodes, supports external plugins via NPM packages, and includes a web dashboard for real-time monitoring.
Available on npm.
Stars
5
Forks
1
Language
TypeScript
License
GPL-3.0
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rse/speechflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TalAter/annyang
💬 Speech recognition for your site
Picovoice/web-voice-processor
A library for real-time voice processing in web browsers
EddyVerbruggen/nativescript-speech-recognition
:speech_balloon: Speech to text, using the awesome engines readily available on the device.
sdkcarlos/artyom.js
A voice control - voice commands - speech recognition and speech synthesis javascript library....
evancohen/sonus
:speech_balloon: /so.nus/ STT (speech to text) for Node with offline hotword detection