# Gradium — Phonon > AI lab announcements, news reports and podcasts. forck.live follows what companies announce about their own products. Press may corroborate an official story; it never leads and never appears as an item of its own. A missing date stays missing. A title is the publisher's words — where a company does not publish in English, an English rendering is listed separately as `Title in English` and named as this site's translation, never as theirs. This file is the record of one model version: what the model registry states about it, Gradium's launch post, the first-party posts this record holds about it, the outlets that reported on those posts, and other companies' announcements that it runs on their platforms. A model ranks nothing here and nothing is composed: each date names whose it is, and a field nothing states is `not stated` rather than missing. - This model's page: https://forck.live/models/phonon - Gradium's page: https://forck.live/company/gradium - Every model: https://forck.live/models - Catalogue: https://forck.live/llms.txt ## Model - Name: Phonon - Company: Gradium (gradium.ai) - Launch post: Open-Sourcing Phonon: A Suite of Frontier On-Device TTS Models — https://forck.live/items/25258-open-sourcing-phonon-a-suite-of-frontier-on-device-tts-models - Announced: 2026-10-20 - Launch source: https://gradium.ai/blog/release-phonon-open-weight - Launch chosen by: a person, pinned in the model registry - Released (per models.dev): 2026-10-20 - Listed (per OpenRouter): not stated - Open weights: yes - Posts about it: 6 - Outlets named under its posts: 1 - Licence: Apache 2.0; CC BY-NC — from https://forck.live/items/25258-open-sourcing-phonon-a-suite-of-frontier-on-device-tts-models - Price: a fixed cost per device and model type, with unlimited generations — from https://forck.live/items/18324-gradium-phonon-on-device-tts-for-consumer-apps-npcs-and-offline-products ## Posts about it _Gradium's own posts whose title names Phonon, and its launch post, in the record's order: dated newest first, undated last. The record reads the newest 50 first-party posts mentioning the model, every company's together, so a model mentioned more often than that lists the newest of them._ Every entry is one first-party announcement, and carries the same eight fields in this order before any others: Company · Announced · Category · Coverage · Announcement · Group · Source · Record `Source` is the company's own page the announcement was traced to and `Record` is this site's page for it. Both are safe to cite. `Coverage` is a number of outlets, or `not counted` — which means this record reached no count of its own, never that nobody wrote about it. `Category` is this tracker's own analysis, and is authoritative wherever it is stated. `not stated` means either that nothing has analysed the post yet or that the analysis placed it outside this taxonomy; neither is a verdict about the announcement. `Announcement` is whether the post is news of something the company did, rather than a how-to, a customer story, a changelog listing or a staffing note. `Group` is which of this record's groups the entry falls in, carried on the entry itself so it holds where the groups are headings and where they are not. One of: `models`, `covered`, `announcements`, `routine`. Anything after `Record` is held detail that only some announcements carry. ### Gradium — Gradium releases Phonon, an open-source text-to-speech model that runs on any device - Company: Gradium (gradium.ai) - Announced: 2026-10-21 - Category: open-weight-release - Coverage: not counted - Announcement: yes - Group: models - Source: https://gradium.ai/blog/gradium-releases-phonon - Record: https://forck.live/items/25740-gradium-releases-phonon-an-open-source-text-to-speech-model-that-runs-on-any - Subject: Gradium TTS / Phonon Gradium released Phonon, an open-source on-device text-to-speech model that generates speech locally on phones, laptops, embedded hardware and in the browser, with no network round-trip or cloud dependency. The company says Phonon has 31m parameters against 82m for Kokoro, the most widely used open on-device TTS model, and that it wins on overall preference in blind human evaluations ahead of Kokoro, Magpie and Pocket TTS. Two variants ship at launch, one with 40 million parameters and one with 31 million, sized to fit inside a mobile app or load in a browser tab. A single multilingual model covers English, French, German, Spanish and Portuguese, with more languages on the roadmap, and it comes with a custom inference codebase that Gradium says is faster than Kokoro and llama.cpp-based runtimes on the same hardware. On desktops and servers with NVIDIA GPUs, the CUDA backend runs inference 8x faster than on CPU, generating the first bit of speech in 5ms on an NVIDIA L40S against 43ms on an AMD EPYC 7413. The model weights are on Hugging Face and the inference code on GitHub under the Apache 2.0 licence, while voice cloning and voice design are available through the Gradium API. ### Gradium — Open-Sourcing Phonon: A Suite of Frontier On-Device TTS Models - Company: Gradium (gradium.ai) - Announced: 2026-10-20 - Category: open-weight-release - Coverage: not counted - Announcement: yes - Group: models - Source: https://gradium.ai/blog/release-phonon-open-weight - Record: https://forck.live/items/25258-open-sourcing-phonon-a-suite-of-frontier-on-device-tts-models - Subject: Gradium TTS / Phonon Gradium is open-sourcing Phonon, a family of 31M and 40M parameter text-to-speech models built to run on-device, from a private beta shaped by early users and partners. Until now, on-device voice meant compromise, with limited language coverage, models too large for the memory budget, or quality too low to ship, the company says. The English Phonon 31m starts speaking in 7 ms on a laptop CPU and ships under Apache 2.0, and Phonon 40m comes as language-specific variants or one multilingual model with a single set of weights. The multilingual model covers English, French, German, Spanish and Portuguese, and all models run on CPU, GPU and NPU across Intel, Arm, WebAssembly, CUDA, Vulkan, Metal, WebGPU, Apple Core ML and Snapdragon. Phonon 31m occupies 64 MB and Phonon 40m 74.6 MB; Gradium also offers custom models for commercial use. ### Gradium — Smaller, clearer, better: Phonon Multilingual beats Magpie and NeuTTS Nano in French, German, and Spanish - Company: Gradium (gradium.ai) - Announced: 2026-07-15 - Category: new-model - Coverage: not counted - Announcement: yes - Group: models - Source: https://gradium.ai/blog/phonon-multilingual-smaller-clearer-better - Record: https://forck.live/items/18311-smaller-clearer-better-phonon-multilingual-beats-magpie-and-neutts-nano-in - Subject: Gradium TTS / Phonon Gradium's 100M-parameter on-device TTS model Phonon produces up to 3.5x fewer word errors than NVIDIA's Magpie TTS in French, German, and Spanish, at 3.6x fewer parameters, and leads other on-device voice-cloning models on word error rate and speaker similarity in every tested language. Phonon clones a reference voice across English, French, German, Spanish, and Portuguese. ### Gradium — Phonon update: 1.00% WER on Seed-TTS, smaller than every model we beat - Company: Gradium (gradium.ai) - Announced: 2026-05-26 - Category: model-update - Coverage: not counted - Announcement: yes - Group: models - Source: https://gradium.ai/blog/phonon-update-may-2026 - Record: https://forck.live/items/18318-phonon-update-1-00-wer-on-seed-tts-smaller-than-every-model-we-beat - Subject: Gradium TTS / Phonon Gradium updated its 100M-parameter on-device TTS model Phonon, reducing word error rate from 1.48% to 1.00% on the Seed-TTS English benchmark and improving speaker similarity from 56.37% to 59.51%. The update removes the previous 100-token minimum input padding and adds int8 quantization support without audio quality loss. Phonon remains in private beta. ### Gradium — Evaluating Phonon: how we made the best TTS model for edge devices - Company: Gradium (gradium.ai) - Announced: 2026-04-09 - Category: research-paper - Coverage: not counted - Announcement: yes - Group: announcements - Source: https://gradium.ai/blog/evaluating-phonon - Record: https://forck.live/items/18323-evaluating-phonon-how-we-made-the-best-tts-model-for-edge-devices - Subject: Gradium TTS / Phonon Gradium's on-device TTS model Phonon (≈100M parameters) achieved a 1.48% word error rate and 56.37% speaker similarity on the Seed-TTS English benchmark, outperforming models 2–5× its size. An update notes that as of May 2026, Phonon reaches 1.00% WER on the same benchmark. Phonon supports voice cloning from a 10-second reference sample and is currently in private beta. ### Gradium — Gradium Phonon: On-Device TTS for Consumer Apps, NPCs, and Offline Products - Company: Gradium (gradium.ai) - Announced: 2026-04-03 - Category: product-launch - Coverage: not counted - Announcement: yes - Group: announcements - Source: https://gradium.ai/blog/gradium-phonon - Record: https://forck.live/items/18324-gradium-phonon-on-device-tts-for-consumer-apps-npcs-and-offline-products - Subject: Gradium TTS / Phonon Gradium announced Phonon, an on-device text-to-speech model that runs entirely on CPU across Android and iOS with no network connection required. Each model is finetuned for one voice, one target language, and one content type, and is shipped as a licensed binary inside the app. Phonon is available through a private beta. ## Who reported on it _Outlets this record can name and link, under the first-party post each one covered. Their number is `Outlets named under its posts` above, and the rows are not totalled again. A post's own `Coverage` can be higher: it counts outlets the signal saw that this record cannot name and link._ ### On: Open-Sourcing Phonon: A Suite of Frontier On-Device TTS Models Record: https://forck.live/items/25258-open-sourcing-phonon-a-suite-of-frontier-on-device-tts-models - MarkTechPost — Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0 (2026-10-22T16:56:12+00:00): https://www.marktechpost.com/2026/10/22/gradium-phonon-31m-on-device-tts/ --- Record: https://forck.live/models/phonon Catalogue: https://forck.live/llms.txt Current issue: https://forck.live/feed.md