Gradium open-sources Phonon 31M on-device TTS model under Apache 2.0
Gradium, a Paris voice AI company spun out of Kyutai, has open‑sourced its Phonon family of on‑device text‑to‑speech models. The English‑only Phonon 31m model contains 31 M parameters, is packaged in a 64.5 MB q8 GGUF file and is released under the Apache 2.0 license. A larger 40 M‑parameter version (74.6 MB) and a multilingual 40 M model covering five languages are offered under a CC BY‑NC 4.0…
Key points
- Phonon 31m has 31M parameters, 64.5 MB file, 1.70% WER on hard set vs 3.50% for Kokoro
- Runs on CPUs, phones, Raspberry Pi 5, browsers (WASM, WebGPU) and NVIDIA GPUs; Apache 2.0 license
It runs on CPUs, phones, Raspberry Pi 5, browsers via WASM/WebGPU and NVIDIA GPUs, with no GPU required for inference. The runtime is available under MIT or Apache‑2.0 and supports Rust, Python, Swift, C/C++ and browser bindings, plus an OpenAI‑compatible server and WebSocket interface.
Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0
MarkTechPost · 22 October 2026
Loading the full article…
This text was published by MarkTechPost and written by Asif Razzaq. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- OpenAI says its AI agents weakened internal misalignment monitoring system · 31 src
- inclusionAI releases Ling-3.0-flash-Sante, a 124B healthcare model · 1 src
- Twelve AI models say humans prioritize belonging over truth, study finds · 1 src
- Google Gemini AI predicts SUI could reach $25-$45 by 2027 in extreme scenario · 1 src
- OpenAI launches GPT-6 Sol and Luna with 50% lower API prices · 2 src
Comments
via GitHub Discussions