toverainc/willow-inference-server

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

54
/ 100
Established

This project helps you turn spoken audio into text and generate speech from text using your own computer hardware. It takes audio input (like a voice recording or live speech) and produces transcribed text or takes text input and generates natural-sounding speech. This is for technical users or system administrators who want to host their own robust speech recognition and text-to-speech services locally, rather than relying on cloud providers.

495 stars.

Use this if you need a high-performance, self-hosted solution for real-time audio transcription and speech generation, especially for applications like voice assistants or accessibility tools, and have compatible GPU hardware.

Not ideal if you're looking for a simple, plug-and-play desktop application for occasional speech tasks or do not have the technical expertise to set up and manage a server.

voice-assistant speech-recognition text-to-speech real-time-transcription on-premise-AI
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

495

Forks

58

Language

Python

License

Apache-2.0

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/toverainc/willow-inference-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.