Open-source Reverb-TTS clones voices 17x realtime, fully local on MacBook M4 Pro via WebGPU
alexcovo_eth · x · 2026-11-20
Software Mansion released Reverb-TTS, an open-source zero-shot voice cloning model built for local inference. Running on their TypeGPU-based ruNNtime engine via WebGPU, it clones a voice at 17x realtime on a MacBook M4 Pro entirely on-device, with SOTA-level quality claims. Demo available.
Related event: Open-Source Reverb-TTS Runs 17x Real-Time Voice Cloning on MacBook(2 posts)→
More from Multimodal
- The Tide Machine: a generative art piece concepted by a human and orchestrated by GPT Astra 6.2 — dreamwieber · 2026-11-20
- Minimax H3 Ref2Va + VHS LoRA: recreating 90s videotape aesthetics — Engine_Hungry · 2026-11-20
- Ideogram 4.6 released, and it's the open-weights version — skipping 4.5 — KokaOP · 2026-11-20
- Google opens Project Genie 4 waitlist access to Google AI Pro subscribers — testingcatalog · 2026-11-20
- Tesseract brings 3D spatial audio generation to Claude and ChatGPT agents — Ror_Fly · 2026-11-20
- a16z hosts Infra AI Studio Summit with portfolio startups ElevenLabs, fal and Ideogram — JenniferHli · 2026-11-20