Gradium open-sources Phonon text-to-speech model
MarkTechPost: Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0
Gradium has open-sourced Phonon, a family of small text-to-speech models built to run on the device. The Gradium Phonon on-device TTS model comes in 31M and 40M sizes. The English Phonon 31m ships under Apache 2.0 and fits in a 64.5 MB file. Developers get natural speech with no cloud call, no GPU and no per-character bill. TL;DR Size: 31M parameters (excluding the audio tokenizer), 64.5 MB q8 GGUF, 24 kHz mono output. Phonon 40m: 40M, 74.6 MB. Runs on: CPUs, phones, Raspberry Pi 5, b
Get smart on it
Phonon is an open-source text-to-speech model that generates speech locally on devices like phones, laptops, and browsers without requiring cloud calls, GPUs, or per-character billing. The 31-million-parameter English version runs on CPUs and various hardware platforms, achieving a 1.70% word error rate on difficult text containing phone numbers and postal codes. Phonon matters because it delivers competitive quality compared to other open models while maintaining small file sizes and fast processing speeds, reaching first audio output in under 7 milliseconds on a MacBook Air CPU and running 3.7 times faster than real time on a Raspberry Pi 5. The model is released under the Apache 2.0 license, with multilingual versions available under a non-commercial license, and can be deployed through multiple frameworks and runtimes including Python, browsers, and compatible platforms like Ollama and LM Studio.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Ai2 releases OlmoEarth v1.3 state-of-the-art AI-ready satellite embeddings for the whole planet
Ai2, the Allen Institute for Artificial Intelligence, today released a satellite map embedding model called OlmoEarth v1.3 and precomputed annual embeddings for the whole planet at various resolutions with a browser-based map-making tool. The model compresses a year of satellite observations into a numerical fingerprint for each 10-by-10-meter patch of ground at the smallest resolution, […] The post Ai2 releases OlmoEarth v1.3 state-of-the-art AI-ready satellite embeddings for the whole pl
Also reported by Hugging Face
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI launched Voxtral 3, a new family of language models built for real-time voice agents. The system combines speech-to-text, text-to-speech, and a voice agent SDK, supports more than 50 languages, and lets agents tap into external tools during live conversations. It can run on your own infrastructure or through EU-hosted APIs to keep data under your control. The article Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time appeared
Also reported by MarkTechPost
Beyond tree cover: mapping the world’s forest types
A global map categorizing every 10-meter patch of land on Earth into distinct forest types.
Recursive launches Flint, a laptop coding model it says was largely built by AI
Startup Recursive has released Flint, a free, laptop-sized coding model built largely by its own AI research system, as an early test of AI that improves itself.
Also reported by Wired AI and MarkTechPost
Voxtral 3
Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages — accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.
Hugging Face’s New AI Biology Model Lets You Chat With DNA
The new open-source model speaks the language of DNA and can help researchers understand the effects of any changes on gene activity and health.