# Gradium — Evaluating Phonon: how we made the best TTS model for edge devices

- Company: Gradium (gradium.ai)
- Announced: 2026-04-09
- Category: not stated
- 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

Update — May 2026: Phonon now reaches 1.00% WER on the same benchmark (down from 1.48%) and 0.83% WER with a fixed voice, beating Kokoro and Magpie. See the latest results in Phonon update: 1.00% WER on Seed-TTS . Phonon is our on-device text-to-speech model: building on continuous audio language models Phonon packages high-fidelity TTS into ~100M parameters, 6x real-time on a single MacBook CPU core, small enough to run in a browser and can reproduce any voice, style and accent. In this post we put it through a standard evaluation and report the results. On the Seed-TTS English benchmark, Phonon achieves a 1.48% word error rate and 56.37% speaker similarity, outperforming models 2x to 5x its size. How we evaluate on-device text-to-speech quality Phonon supports on-device voice cloning: given a 10-second sample of someone's voice, it generates new speech that matches that speaker's tone, accent, and cadence. This is what makes a lightweight, on-device TTS model useful in practice. A navigation app can speak in the user's preferred voice. A language learning tool can maintain a consistent teacher voice across sessions. …

---

Record: https://forck.live/items/18323-evaluating-phonon-how-we-made-the-best-tts-model-for-edge-devices
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md