# Hugging Face — A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.

- Company: Hugging Face (huggingface.co)
- Announced: 2026-11-05
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/phonon-tts
- Record: https://forck.live/items/32025-a-closer-look-at-phonon-tts-launching-high-quality-on-device-speech-that-tops
- Subject: Platform
- Open weights: yes
- Models affected: Phonon 31m, Phonon 40m
- License: Apache 2.0

Phonon is a small on-device text-to-speech model that runs offline without a server or network, released two weeks before this post. It comes in two sizes, about 65 MB and 75 MB, together covering English, French, German, Spanish and Portuguese, with more than 100 built-in voices and custom voice creation in Gradium Studio. Phonon 31m speaks English and is Apache 2.0, so it can be used free including commercially; Phonon 40m covers all five languages under a non-commercial CC BY-NC license, and commercial use of those models is priced by number of users rather than speech generated. According to the Hugging Face Open TTS Leaderboard, Phonon ranks first in German and Spanish on intelligibility and in the top three in every language evaluated, next to models up to 100 times its size, and tops the CPU streaming benchmark on time-to-first audio. It runs on phones, laptops, single-board computers and in a browser tab, and was downloaded more than 200,000 times in its first two weeks. A separate inference framework, ptts, supports more than 10 backends across CPU, GPU and NPU, while Phonon is available in Transformers from v5.21 as its reference PyTorch implementation for batched GPU generation.

## Evidence

Verbatim from https://huggingface.co/blog/phonon-tts:

> Two weeks ago, we opened up Phonon, our small text-to-speech model that runs on your own device. It needs no server and no network, and what you type stays with you.
> 
> We've been very happy with the reception so far. So here's the story of the launch: why we built Phonon, what it can do, the demos that came with it, and how it did on Hugging Face's Open TTS Leaderboard.
> 
> Why a voice should live on your device
> 
> Most voice AI lives in the cloud: every sentence makes a round trip to a server. Phonon runs on your own device instead. Your text stays there and the voice works without a network. We’ve also opened the weights. Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC, so they’re free for non-commercial projects. If you’re building something commercial with those, pricing is based on your number of users, not how much speech you generate.
> 
> Getting a good voice to run on a small device has always been hard. You could make the model small, but then it didn’t sound great. Or you could make it sound great, but then it wouldn’t fit. We addressed both.

---

Record: https://forck.live/items/32025-a-closer-look-at-phonon-tts-launching-high-quality-on-device-speech-that-tops
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md