Gradium open-sources Phonon, 31M-40M on-device TTS models with 1.7% WER
thisguyknowsai · x · 2026-10-20
Gradium has open-sourced Phonon, a family of 31M and 40M-parameter on-device text-to-speech models that work offline and can ship inside any app.
Key numbers:
- Phonon 31m (English) hits a 1.70% word error rate on 500 hard sentences (phone numbers, emails, postal codes), far ahead of Kokoro (3.50%), Kitten TTS (7.40%) and NeuTTS Nano (8.71%)
- Phonon 40m multilingual scores 2.11% WER
- Phonon-31m is released under Apache 2.0 with broad inference support
Gradium also extended its seed funding to $100M with NVIDIA among new investors and opened a Bay Area office.
Related event: Gradium Open-Sources Phonon: Sub-50M On-Device TTS with 1.7% WER(6 posts)→
More from Models
- Ternary-Bonsai-2-9B: 2-bit ternary vision-language model trends on Hugging Face for on-device use — prism-ml · 2026-10-21
- Grok Bot DAU hits new peak as users report it books flights and pays bills — elonmusk · 2026-10-21
- Interconnects: China proposes export pre-approval for frontier models as DHS bars DeepSeek from federal procurement — natolambert · 2026-10-21
- Researcher urges the community to stop using PickScore as a reward model, recommends HPSv3 instead — gowthami_s · 2026-10-21
- OpenAI boosts COBOL, Fortran and Visual Basic support to modernize legacy enterprise systems — CurieuxExplorer · 2026-10-21
- NVIDIA Hosts Ask-the-Experts Session on Nemotron 3.5 Super VL — NVIDIAAI · 2026-10-21