phonon-31m English

High-quality Text-to-Speech, on your device.

phonon-31m is a text-to-speech model from the Phonon family. It turns text into natural 24 kHz speech in English. It streams audio while it is still generating, and it is small enough to run in a browser tab, on a phone, or on a laptop CPU.

Phonon builds on Pocket TTS and the Mimi codec, developed by Kyutai.

Try it in your browser · All Phonon models · Runtime on GitHub · Python · Browser · Discord

Model details

Model type: text-to-speech. A flow-matching transformer predicts audio latents from the text one 80 ms frame at a time, and the Mimi codec's decoder turns them into audio.
Parameters: 31M (excluding the audio tokenizer)
Weights file: model.q8.gguf, 64.5 MB (8-bit quantized)
Languages: English
Output: mono, 24 kHz
License: Apache 2.0

The Phonon family

Model	Parameters	q8 weights	Languages	License
phonon-31m-en	31m	64.5 MB	English	Apache 2.0
phonon-40m-en	40m	74.6 MB	English	CC BY-NC 4.0
phonon-40m-fr	40m	74.6 MB	French	CC BY-NC 4.0
phonon-40m-de	40m	74.6 MB	German	CC BY-NC 4.0
phonon-40m-es	40m	74.6 MB	Spanish	CC BY-NC 4.0
phonon-40m-pt	40m	74.6 MB	Portuguese	CC BY-NC 4.0
phonon-40m-multilingual	40m	74.6 MB	All 5 languages	CC BY-NC 4.0

All of them run on the same runtime and use the same file layout, so switching models means changing the repo ID.

Quickstart

Every runtime names this model as hf://gradium/phonon-31m-en, and takes lang, which selects how text is normalized (numbers, symbols, dates). This model speaks English, so use en.

Command line

uvx ptts --lang en --quant q8 \
  --voice Easton "Hello from Phonon." -o speech.wav

uvx runs the Python package's command without installing it. The standalone ptts binary from GitHub Releases or Homebrew (brew install gradium-ai/tap/ptts) takes the same flags.

Python

pip install ptts

import ptts

tts = ptts.TTS("hf://gradium/phonon-31m-en", lang="en", quant="q8")
tts.save("speech.wav", "Hello from Phonon.", voice="Easton")

# Or stream: chunks arrive while the rest is still being generated.
with tts.stream("Speech can start playing right away.", voice="Easton") as audio:
    for pcm in audio:
        ...  # float32 chunks at audio.sample_rate

Transformers usage 🤗

Install 🤗 Transformers from source:

pip install git+https://github.com/huggingface/transformers

from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from transformers import AutoProcessor, GradiumPhononTTSForConditionalGeneration

model_id = "gradium/phonon-31m-en"
processor = AutoProcessor.from_pretrained(model_id, device_map="auto")
model = GradiumPhononTTSForConditionalGeneration.from_pretrained(model_id, device_map="auto")

# Easton (en-us); every voice and its ID: https://huggingface.co/gradium/phonon-voices
voice_path = hf_hub_download("gradium/phonon-voices", "voices/LMDIYE0Oa377Qh6Z.safetensors")
voice = load_file(voice_path)["speaker_wavs"][0].T.float()  # (num_frames, 512)

conversation = [
    {"role": "user", "content": [{"type": "audio"}, {"type": "text", "text": "Hello from Phonon."}]}
]
inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    return_dict=True,
    add_generation_prompt=True,
    processor_kwargs={"audio_prompt_latents": [voice]},
).to(model.device)

outputs = model.generate(**inputs)
audio = processor.decode(outputs.audio_latents, outputs.audio_latents_mask)
processor.save_audio(audio, "speech.wav")

This repo's default-voice.safetensors loads the same way. Unlike the runtime, the tokenizer does not spell out numbers, amounts, symbols or addresses, and long text is split with processor.split_text: see the Transformers docs.

Other platforms

Platform	Guide
Python scripts and backends	`ptts` on PyPI · Python guide
Web apps, in the browser	`phonon-tts` on npm · Browser guide
iPhone, iPad and Mac apps (Core ML)	Swift guide
Android apps	Android guide · Snapdragon NPU preview
Android system voice, for TalkBack and every app that uses `TextToSpeech`	Android TTS engine
Server with an OpenAI-compatible API (Docker)	Server guide
Home Assistant	Home Assistant setup
Streaming over WebSocket	WebSocket server
Rust	`ptts` on crates.io · Rust guide
C and C++	`ptts.h`

Voices

Phonon comes with a catalog of ~100 voices available in the gradium/phonon-voices repo. Instant voice cloning and voice design are available through the Gradium studio.

Benchmarks

Phonon was compared with other open text-to-speech models on three measures, per language:

Elo: human preference from blind pairwise listening tests (higher is better).
Hard set LLM WER: word error rate on hard sentences full of structured data (numbers, dates, codes, units), scored with an LLM-assisted ASR comparison (lower is better).
Seed-TTS LLM WER: the same metric on the Seed-TTS evaluation sentences (lower is better).

In every language, a Phonon model is first on all three measures.

English (US) (Elo from 468 raters, 8,290 votes)

Model	Elo	Hard set LLM WER	Seed-TTS LLM WER
phonon-31m-en	2098	1.5%	0.51%
phonon-40m-en	2117	2.3%	0.45%
phonon-40m-multilingual	2097	2.0%	0.48%
Kokoro	2043	3.5%	0.45%
Magpie	1939	28%	0.46%
NeuTTS	2034	8.7%	0.62%

French (Elo from 172 raters, 2,270 votes)

Model	Elo	Hard set LLM WER	Seed-TTS LLM WER
phonon-40m-fr	2072	2.4%	1.3%
phonon-40m-multilingual	2016	2.7%	1.5%
Kokoro	1578	5.5%	1.8%
Magpie	1608	30%	2.0%
NeuTTS	1853	9.9%	2.7%

German (Elo from 168 raters, 2,220 votes)

Model	Elo	Hard set LLM WER	Seed-TTS LLM WER
phonon-40m-de	2097	2.2%	0.83%
phonon-40m-multilingual	2046	2.9%	0.90%
Magpie	1640	29%	1.6%
NeuTTS	1768	9.3%	2.6%

Spanish (Spain) (Elo from 201 raters, 2,290 votes)

Model	Elo	Hard set LLM WER	Seed-TTS LLM WER
phonon-40m-es	2103	2.1%	0.85%
phonon-40m-multilingual	2076	2.6%	1.0%
Kokoro	1629	3.8%	0.93%
Magpie	1870	25%	0.92%
NeuTTS	1778	16%	5.1%

Portuguese (Brazil) (Elo from 171 raters, 2,000 votes)

Model	Elo	Hard set LLM WER	Seed-TTS LLM WER
phonon-40m-pt	2144	2.9%	1.1%
phonon-40m-multilingual	2048	3.2%	1.1%
Kokoro	1633	4.1%	1.3%

Intended use

Phonon is made for applications that speak on the user's device: offline and private assistants, screen readers and other accessibility tools, games, and interactive apps that cannot wait for a cloud round trip. It also runs as a local server with an OpenAI-compatible API and as a voice for Home Assistant.

Limitations

The model speaks only the languages above. Text in other languages is read with the wrong pronunciation.
Text is normalized before synthesis (numbers, currency, dates, emails and so on), and that step needs the right language. Choose lang to match the text.
Very long inputs are split into sentences and spoken one after the other, so prosody does not carry across the whole text.

Responsible use

Do not use Phonon to impersonate a real person, to deceive listeners about who is speaking, or to clone a voice without the speaker's consent. Tell listeners when speech is synthetic where that matters to them.

License

The weights, tokenizer and voices in this repository are released under Apache 2.0, which allows commercial use. The runtime is a separate project, licensed MIT OR Apache-2.0.