🎙️ Real-time interpretation, powered locally by VoxCPM2.
This is a AI post classified by Jev as Voice AI (a tool drop), kept by the AI Radar because it carries real work, not commentary.
🎙️ Real-time interpretation, powered locally by VoxCPM2. Developer @HenryZ30734018 built VoxWeft, an open-source simultaneous interpretation system for Apple Silicon. It uses an MLX implementation of VoxCPM2 to turn live speech into translated speech on-device, keeping audio private and responsive. ✨ Highlights: ⚡ VoxCPM2 streams first audio in ~170 ms on an M5 MacBook 🌍 Generates speech across 30 languages, supporting direct language-pair interpretation without a pivot 🗣️ Clones a target voice from ~5 seconds of reference audio for a consistent interpreted voice 💻 Runs in 4-bit quantization
Posted by OpenBMB (10.8k followers) 1 h ago · 15 likes · 441 views · view the original post on X. Kept by the AI Radar as Voice AI. Tools mentioned: voxweft, voxcpm2.
More AI work like this
- If your voice interaction is failing, you should be able to know why. — @ai_coustics
- Gemini 3.1 Flash TTS is already #1 — @HarshithLucky3
- Another speech-to-text model release: — @vikhyatk
- Gemini 3.8 Flash TTS model appeared on Google Cloud Quotas — @HarshithLucky3
- And yet another flash model 🥲 , — @mrfanduu
- Native Audio. The future sounds amazing! — @gospaceport
- Announcing the Artificial Analysis Pronunciation Robustness benchmark, measuring how… — @ArtificialAnlys
- GREAT QUESTION!!!!! — @WaitWhat
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 41.6k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 14:03 UTC. Full method.