izwi-ai/izwi
On-device AI engine for transcription, TTS, and voice workflows.
Izwi is an on-device AI engine that helps you work with audio and voice without sending your data to the cloud. You can feed it spoken audio to get text transcripts, or give it text and get back natural-sounding speech. This is ideal for anyone who needs to process voice or create audio content while keeping their data completely private and secure.
181 stars.
Use this if you need to convert speech to text, generate speech from text, or build interactive voice AI experiences, and strict data privacy is a top concern.
Not ideal if you primarily need cloud-based scalability for very large-scale audio processing or prefer a fully managed online service.
Stars
181
Forks
18
Language
Rust
License
—
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/izwi-ai/izwi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TrevorS/voxtral-mini-realtime-rs
Streaming speech recognition running natively and in the browser. A pure Rust implementation of...
darkautism/sensevoice-rs
A Rust-based, SenseVoiceSmall
mrtozner/vox
Local voice AI framework for Rust. Whisper + LLM + TTS with no cloud dependencies.
0xPD33/sonori
Sonori is a fully local STT app for Linux (Wayland).
CodersCreative/faster-whisper-rs
a rust crate for easily implementing faster-whisper stt into your rust programs.