Gradium open-sourced its on-device TTS

Gradium released Phonon, an open-weight on-device text-to-speech model family small enough to ship in any app and run offline without a graphics card. The Phonon lineup includes 31m, 40m and 40m multilingual models, runs on laptops, desktops, Android phones and a Raspberry Pi 5, and reaches up to 22× faster than real time on an iPhone 16 Pro via a Swift package using Apple's AI chip. Gradium says the 31m English model was tested on 500 sentences other models get wrong, covering phone numbers, email addresses and postal codes, and the code is available at github.com/gradium-ai/xn-ptts.

Harry Potter hat voice Autonomous's robot, Lamp, puts on a sorting hat and talks in character, voiced by Phonon. Introducing Gradium's open-weight text-to-speech, small enough to ship in any app. Private, and it works offline. Already trusted by 1.7% Phonon 31m · English Tested on 500 sentences that other models get wrong: phone numbers, email addresses, postal codes. Phonon 1.0 Phonon 31m Phonon 40m Phonon 40m multilingual Where it runs Laptops, desktops, Android phones, even a Raspberry Pi 5. No graphics card needed. On Apple's own AI chip, through a Swift package. Up to 22× faster than real time on an iPhone 16 Pro. Runs in the visitor's browser, so their text never leaves their device. The demo at the top of this page is it. When there is one, for the fastest speech: NVIDIA, Apple, Vulkan or WebGPU, chosen when you build it. Compatible with Paste one of these prompts into your coding agent and it will read the README, build Phonon and make it speak. Or take the code. 1Set up Phonon, Gradium's on-device text-to-speech, from https://github.com/gradium-ai/xn-ptts. 2 3Read the README first and follow it over anything you assume. 4 51. Install the Rust CLI from the repository root with 6 cargo install --path ptts --locked --features cli. 72. Point MODEL DIR at the model folder config.json, model.q8.gguf, 8 tokenizer.json and the voices . 93. Synthesize "Hello world" with --lang en --quant q8 --voice Freya 10 to out.wav. 11 12Verify the file plays and tell me how to change the voice. Text in, a WAV out. The fastest way to hear it. 1 Creazione di Adamo https://www.museivaticani.va/content/museivaticani/it/collezioni/musei/cappella-sistina/volta/storie-centrali/creazione-di-adamo.html , by Michelangelo Buonarroti. Date: c. 1511, part of the ceiling painted 1508-1512. Material: fresco. Dimensions: 280 × 570 cm. Current location: Cappella Sistina, volta, Musei Vaticani, Vatican City. 2 Les trois Grâces https://collections.louvre.fr/ark:/53355/cl010276682 . Artist: unknown; Roman, with restorations by Nicolas Cordier and Amainci, 1609. Date: 2nd century AD ? . Material: marble, probably Greek. Dimensions: h. 123 cm, w. 86 cm, d. 29 cm. Current location: Musée du Louvre, Aile Sully, Salle 348, Paris. Inventory number: Ma 287; MR 211; N 642. 3 Victoire de Samothrace https://collections.louvre.fr/en/ark:/53355/cl010252531 . Artist: unknown, Rhodes ? . Date: c. 200-175 BC. Material: Parian marble for the figure, grey Lartos marble for the ship. Dimensions: h. 328 cm overall. Current location: Musée du Louvre, Aile Denon, Escalier Daru, Salle 703, Paris. Inventory number: Ma 2369; NIII 2447; MNB 2118; MNC 1433. 4 Portrait de Juliette Récamier, née Bernard 1777-1849 https://collections.louvre.fr/en/ark:/53355/cl010059215 , by Jacques-Louis David. Date: 1800. Material: oil on canvas. Dimensions: h. 174 cm, w. 244 cm. Current location: Musée du Louvre, Aile Denon, Salle 702, Salle Daru, néoclassicisme, Paris. Inventory number: INV 3708; C 124.