Gradium open-sources Phonon 31m, a 31M-parameter on-device TTS model under Apache 2.0
Gradium has open-sourced Phonon, a family of on-device text-to-speech models. The English Phonon 31m has 31M parameters, ships under Apache 2.0, fits in 64.5 MB, and starts speaking in about 7 ms on a laptop CPU.
Gradium has open-sourced Phonon, a family of on-device text-to-speech (TTS) models. The English model, Phonon 31m, is released under the Apache 2.0 license, according to a MarkTechPost report published October 22, 2026.
Key specifications
- Model: Phonon 31m (English), part of the Phonon family
- Parameters: 31M
- Size on disk: 64.5 MB
- Latency: starts speaking in about 7 ms on a laptop CPU
- License: Apache 2.0
- Deployment target: on-device
Pricing, context window and benchmark scores were not part of the report.
What this means
Phonon 31m's stated footprint of 64.5 MB and its roughly 7 ms time to first speech on a laptop CPU place it in the category of TTS models built to run locally rather than through a hosted API. The Apache 2.0 license is a standard open-source license, so the weights are available for developers to use under its terms. Because Phonon is described as a family, additional models beyond the English 31m variant are part of the release.
Related Articles
NVIDIA releases Kumo Forecast, an Apache 2.0 time-series model built on a ~340M-parameter MOMENT-1-large encoder
NVIDIA has released Kumo Forecast (formerly NV-Tesseract Forecasting), a multivariate time-series forecasting model under Apache 2.0. It pairs a frozen MOMENT-1-large encoder of roughly 340 million parameters with a trainable forecasting head, optional nearest-neighbor retrieval over historical data (DARR), and a built-in interpretability framework.
iFLYTEK releases Spark X2.6, a 293B-A30B MoE model trained on domestic compute
At its 1024 developer festival, iFLYTEK released Spark X2.6, a 293B-A30B mixture-of-experts model trained on domestic compute. The company also open-sourced the on-device Spark X2.6-4B and debuted the SparkAudio 1.0 speech model.
Xiaomi open-sources Xiaomi-Lens-0, a 4B multimodal model that outputs pixel-level mask tokens mid-answer
Xiaomi's SeerRay-Lab has open-sourced Xiaomi-Lens-0, a 4B multimodal model built on Qwen3.5-4B. The model emits mask tokens for pixel-level image regions in the middle of an answer. The lab also released a benchmark called LensBench.
China Telecom open-sources Xing4.0-29B-Intent, a 29B intent model, with 2.753M-sample training corpus
China Telecom's Xingchen General AI Lab has released and open-sourced Xing4.0-29B-Intent, a model that turns a user's sentence into structured JSON covering intent and parameters. The release includes model weights, a 2.753 million-sample training corpus and an inference image. In the company's own tests, it scores 58 against a top score of 49 among general-purpose models.
Comments
Loading...