Pinokio
FeedAppsRemoteCreate
Download Pinokio
Sign inCreate accountJoin
Sign inCreate accountJoin

Post

Conversation
Pierre Bruno@pierrunoytΒ·1h

πŸ”Š Phonon TTS is now on Pinokio: 1-click install

Phonon is Gradium's family of small text-to-speech models (31M–40M parameters). They run entirely on your CPU and
don't need a GPU or PyTorch.

🎧 What it does

🌍 Reads text aloud in English, French, German, Spanish and Portuguese. One multilingual model covers all five.
🧠 Includes all 7 Phonon models: phonon-31m-en plus the 40m models for en, fr, de, es, pt and multilingual.
πŸŽ™οΈ Comes with about 100 voices, filtered by language. Each voice downloads the first time you use it.
πŸ”’ Spells out numbers, currency, dates and symbols in the selected language, so "$5" is read as "5 dollars".
🎚️ Has a speed slider and outputs natural 24 kHz WAV.
πŸ”Œ Includes a local Gradio API at /generate for your own apps and scripts.

πŸ’¬ Example

The meeting moved to 3:30 PM on 12/05, and tickets now cost $5.

πŸ“‹ Before you install

πŸ’» Runs on Windows, Linux and macOS. On x86_64 Windows and Linux the CPU needs AVX2/FMA (most CPUs from 2015 on). Each
model is only 65–75 MB.

πŸ”‘ phonon-31m-en works out of the box with no account and is Apache 2.0.
The 40m models are gated. Accept their terms on Hugging Face, then paste a read token into the launcher's πŸ”‘ Hugging
Face Token button. You don't need to restart.
https://huggingface.co/collections/gradium/phonon

πŸ“„ The 40m models are CC BY-NC 4.0, so they're for non-commercial use only.

πŸ‘‰ Install β†’ Start β†’ Generate

https://github.com/PierrunoYT/Phonon-TTS-Pinokio

Phonon TTSPierrunoYT/Phonon-TTS-Pinokio
#announcement#audio#phonon#tts
Loading conversation…

Replies

Post context

App used

Phonon TTSPierrunoYT/Phonon-TTS-Pinokio

On-device text-to-speech with all 7 Phonon models (31m English + 40m en/fr/de/es/pt/multilingual), ~100 voices, CPU-only, no PyTorch

View app

Published by

@pierrunoyt1h ago
#announcement#audio#phonon#tts
Pinokio
PrivacyTerms
FeedAppsCreateRemote

Post context

App used

Phonon TTSPierrunoYT/Phonon-TTS-Pinokio

On-device text-to-speech with all 7 Phonon models (31m English + 40m en/fr/de/es/pt/multilingual), ~100 voices, CPU-only, no PyTorch

View app

Published by

@pierrunoyt1h ago
#announcement#audio#phonon#tts

Related posts

Maestro: {"ok":false,"dispatched":false,"error":"Cannot find module '…/pterm/endpoint.js'\nRequire stack…@aidous Β· 17d agoAkiFactory is live β€” one topic, a finished short video, and an optional AI cover@mvrdvk Β· 27d agoComfyui: open in SAM detector cannot be found while right click on load image@nicopin Β· 1mo ago