Gradium open-sources Phonon on-device TTS: 31m model hits 1.7% WER, beating Kokoro
alex_verem · x · 2026-10-21
Voice AI startup Gradium open-sourced Phonon, a family of 31m/40m-parameter on-device TTS models that run offline and private in any app. On 500 sentences models typically fumble (phone numbers, emails, postal codes), Phonon 31m achieves a 1.70% word error rate vs 2.11% for the 40m multilingual, 3.50% for Kokoro, 7.40% for Kitten TTS, and 8.71% for NeuTTS Nano. 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 Models(7 posts)→
More from Venture
- The AI revenue death-spiral scenario: capex, rate pressure, and startups cutting token spend — menhguin · 2026-10-21
- AI bubble author clarifies: legit ROI use cases, but heavy users are all inside the AI ecosystem — menhguin · 2026-10-21
- The 'ARR Ouroboros': why VC-funded AI startups selling to each other could trigger a death spiral — menhguin · 2026-10-21
- Cutting 'AI agents' from his landing page dropped Meta CPA by 70% — tyler_agg · 2026-10-21
- Nvidia guides 70% growth citing unmet AI demand, while media panics over a $500M Korean neocloud IPO — firstadopter · 2026-10-21
- MCP Platform NitroStack Wins Product Hunt Product of the Day, Focuses on Retention — EstablishmentFun4373 · 2026-10-21