Understand this story
Gradium has open-sourced the Phonon series of on-device text-to-speech models. According to a MarkTechPost report on October 23, 2026, the English version Phonon 31m has 31M parameters and is a 64.5 MB q8 GGUF file, uses the Apache 2.0 license, and outputs 24 kHz mono audio; the model requires no GPU and can run on CPU, phones, Raspberry Pi 5, and browsers, producing the first audio segment in 6.9 ms on a MacBook Air M5 CPU, with a WER of 1.70% on Gradium's self-tested 500-sentence hard set, compared with Kokoro's 3.50%. The same report states that the 40m version covers five languages—English, French, German, Spanish, and Portuguese—but uses the CC BY-NC 4.0 non-commercial license. There are currently no subsequent development facts.
AI-generated from public reports
Latest development · Report
Gradium Open-Sources Phonon On-Device TTS Models, 31M Version Uses Apache 2.0Developments
1 confirmed developments
- Source:MarkTechPost
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
MarkTechPost
Gradium Open-Sources Phonon On-Device TTS Models, 31M Version Uses Apache 2.0
Gradium has open-sourced the Phonon series of on-device text-to-speech models. The English version, Phonon 31m, has 31M parameters and a 64.5 MB q8 GGUF file, uses the Apache 2.0 license, and outputs 24 kHz mono audio. The model runs without a GPU on CPUs, phones, Raspberry Pi 5, and in browsers. On a MacBook Air M5 CPU, it produces the first audio segment in 6.9 ms, and on Gradium's self-tested 500-sentence hard set it achieves a WER of 1.70%, compared with 3.50% for Kokoro. The 40m version covers five languages—English, French, German, Spanish, and Portuguese—but uses the CC BY-NC 4.0 non-commercial license.