{"slug": "gradium-open-sourced-its-on-device-tts", "title": "Gradium open-sourced its on-device TTS", "summary": "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.", "body_md": "### Harry Potter hat voice\n\nAutonomous's robot, Lamp, puts on a sorting hat and talks in character, voiced by Phonon.\n\nIntroducing\n\nGradium's open-weight text-to-speech, small enough to ship in any app. Private, and it works offline.\n\nAlready trusted by\n\n1.7%\n\nPhonon 31m · English Tested on 500 sentences that other models get wrong: phone numbers, email addresses, postal codes.\n\nPhonon 1.0\n\nPhonon 31m\n\nPhonon 40m\n\nPhonon 40m multilingual\n\nWhere it runs\n\nLaptops, desktops, Android phones, even a Raspberry Pi 5. No graphics card needed.\n\nOn Apple's own AI chip, through a Swift package. Up to 22× faster than real time on an iPhone 16 Pro.\n\nRuns in the visitor's browser, so their text never leaves their device. The demo at the top of this page is it.\n\nWhen there is one, for the fastest speech: NVIDIA, Apple, Vulkan or WebGPU, chosen when you build it.\n\nCompatible with\n\nPaste one of these prompts into your coding agent and it will read the README, build Phonon and make it speak. Or take the code.\n\n```\n1Set up Phonon, Gradium's on-device text-to-speech, from https://github.com/gradium-ai/xn-ptts.\n2\n3Read the README first and follow it over anything you assume.\n4\n51. Install the Rust CLI from the repository root with\n6   cargo install --path ptts --locked --features cli.\n72. Point MODEL_DIR at the model folder (config.json, model.q8.gguf,\n8   tokenizer.json and the voices).\n93. Synthesize \"Hello world\" with --lang en --quant q8 --voice Freya\n10   to out.wav.\n11\n12Verify the file plays and tell me how to change the voice.\n```\n\nText in, a WAV out. The fastest way to hear it.\n\n[ 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.\n\n[ 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.\n\n[ 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.\n\n[ 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.", "url": "https://wpnews.pro/news/gradium-open-sourced-its-on-device-tts", "canonical_source": "https://gradium.ai/phonon", "published_at": "2026-10-20 17:06:22+00:00", "updated_at": "2026-10-20 17:17:02.310406+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "ai-products", "machine-learning"], "entities": ["Gradium", "Phonon", "Phonon 31m", "Phonon 40m", "Phonon 40m multilingual", "Raspberry Pi 5", "iPhone 16 Pro", "Autonomous"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/gradium-open-sourced-its-on-device-tts", "markdown": "https://wpnews.pro/news/gradium-open-sourced-its-on-device-tts.md", "text": "https://wpnews.pro/news/gradium-open-sourced-its-on-device-tts.txt", "jsonld": "https://wpnews.pro/news/gradium-open-sourced-its-on-device-tts.jsonld"}}