Gradium open-sources Phonon on-device TTS: 31M model hits 1.7% WER
bigaiguy · x · 2026-10-20
- Gradium released and open-sourced Phonon, a family of on-device text-to-speech models (31M and 40M parameters) small enough to embed in any app, running offline with private, on-device inference.
- Accuracy: Phonon 31M (English) scores 1.70% WER on 500 sentences that trip up other models (phone numbers, emails, postal codes); Phonon 40M multilingual hits 2.11% and 40M English 2.22%, well ahead of Kokoro (3.50%), Kitten TTS (7.40%) and NeuTTS Nano (8.71%).
- The company also extended its seed funding to $100 million with NVIDIA joining as an investor, and opened a Bay Area office to scale real-time voice AI.
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