Skip to content
Hot storiesContinuously updated

Gradium开源端侧文本转语音模型Phonon TTS

1 reports1 reporting sourcesUpdated 15 hours ago

Start here

AI overview

2026年11月5日，Gradium正式开源端侧文本转语音模型Phonon TTS。该模型无需服务器或网络支持，可在手机、电脑或单板机上完全离线运行。架构方面，Phonon TTS基于Pocket TTS谱系与flow matching技术构建。模型提供两种尺寸版本：31m版本体积约65 MB，支持英文，采用Apache 2.0开源协议，允许商用；40m版本体积约75 MB，支持英语、法语、德语、西班牙语和葡萄牙语五种语言，采用CC BY-NC非商业许可协议。

AI-generated from reports · Updated 4 hours ago

Latest developmentsNov 5 08:00
Gradium正式开源端侧TTS模型Phonon TTS，提供31m与40m两种尺寸版本。

Report timeline

Follow the reports to see different sides of the story.

Nov 5
  1. Hugging FaceSelected
    Open-Source On-Device Text-to-Speech Model Phonon TTS Released

    Gradium has officially open-sourced Phonon TTS, an on-device text-to-speech model that runs entirely offline on smartphones, PCs, or single-board computers without requiring servers or internet access. Built on the Pocket TTS lineage and flow matching technology, the model is available in two sizes: a 31M version (approx. 65 MB, English only, commercially licensed under Apache 2.0) and a 40M version (approx. 75 MB, supporting five languages: English, French, German, Spanish, and Portuguese, under a CC BY-NC license).

Story heat trend

Current heat 7·Comparable peak 7（Nov 5 19:00）·Comparable change, last 24 hours–

02468Nov5Nov5Nov5Nov5

Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.