Models & Labs
Phonon TTS: High-Quality On-Device Speech
Hugging Face Bloghigh confidence
Why it matters
- →Enables privacy-first voice synthesis by running entirely offline on consumer hardware.
- →Achieves state-of-the-art speed and quality metrics with a model under 32M parameters.
- →Provides Apache 2.0 licensed weights, allowing unrestricted commercial integration.
Hugging Face and Gradium have launched Phonon, an open-source text-to-speech model designed for on-device inference. The 31-million-parameter model runs locally on CPUs, GPUs, and NPUs, eliminating the need for cloud servers. It currently supports English, French, German, Spanish, and Portuguese, with voice cloning capabilities available via Gradium Studio. Phonon ranks first in speed benchmarks on the Hugging Face Open TTS Leaderboard and leads in intelligibility for German and Spanish.
Read originalThe story around this
TopicOllama Adds Local Text To Speech
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1NVIDIA Magpie TTS Enhances Multilingual Voice Agents
Hugging Face Blog · August 10, 2026 · Background
- 2Relay Debuts AI-Powered Voice-to-Text Microphone
WIRED AI · August 27, 2026 · Background
- 3BreezeTTS2: Real-time local voice synthesis
Sam Witteveen · August 31, 2026 · Related
- 4Google Gemini 3.8 Flash TTS with Voice Cloning
Sam Witteveen · September 24, 2026 · Background
- 5Hugging Face launches objective Open TTS Leaderboard
Hugging Face Blog · September 30, 2026 · Related
- 6Ollama adds local TTS with Phonon and MLX acceleration
Ollama Blog · October 24, 2026 · Same story
- 7llama.cpp adds Soprano TTS support
llama.cpp Releases · October 24, 2026 · Related
- 8llama.cpp adds PocketTTS voice cloning support
llama.cpp Releases · November 3, 2026 · Background
What happened next
- 9Underdog demos 32MB local speech model
TechCrunch AI · November 6, 2026 · Background
More from Hugging Face Blog
© Hugging Face BlogResearchagents
ToyBlocks: Controlled simulation for robot learning research
Hugging Face launched ToyBlocks, a controlled simulation framework designed to isolate and study the specific mechanics of robot learning. By focusing on a simple tabletop environment with blocks, it allows researchers to automatically generate massive datasets of tasks and demonstrations without manual teleoperation. This setup enables precise testing of how high-level reasoning models like Molmo 2 interact with low-level action controllers like ManiFlow. The real value lies in reproducibility; scientists can now systematically vary training data to understand exactly why a robot fails or succeeds, moving beyond the black-box nature of current robotics benchmarks.
Hugging Face Blog
© Hugging Face BlogResearchother
Open ASR Leaderboard adds Egyptian and Nigerian English
The Open ASR Leaderboard is expanding its evaluation scope by adding private test sets for Egyptian and Nigerian English, addressing a significant gap in global representation. This update moves beyond the traditional Inner Circle accents to include Outer and Expanding Circle varieties, providing a more realistic benchmark for speech recognition models. By partnering with Liva AI for data collection, Hugging Face ensures these evaluations reflect natural, high-context user interactions rather than artificial tasks. This shift forces developers to optimize for diversity, making model performance metrics more trustworthy and globally relevant.
Hugging Face Blog
© Hugging Face BlogModels & Labsvideo
NVIDIA Cosmos 3 Open Models for World Simulation
NVIDIA is opening up its Cosmos 3 world model family with four new 16B parameter checkpoints, shifting from closed research to open-weight simulation. The release targets two critical domains: autonomous driving and robotics. For self-driving cars, the models generate synchronized camera video and LiDAR data, solving the alignment problem between visual appearance and 3D geometry. For robotics, Sim-Bimanual predicts environmental changes from robot actions, enabling closed-loop policy training. This moves world modeling from passive video generation to interactive simulation where agents can act and observe consequences.
Hugging Face Blog
More in Models & Labs
Models & Labsother
llama.cpp b12177 adds CUDA 13 and ROCm 10
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13.5 and ROCm 10.0 alongside existing CUDA 12 builds. AMD GPU users finally get first-class parity with NVIDIA, while Snapdragon mobile chips gain dedicated NPU acceleration paths. Apple Silicon KleidiAI is explicitly disabled here, a notable regression for Mac performance that suggests ongoing tuning issues. The inclusion of OpenVINO and SYCL backends further cements llama.cpp as the universal runtime for inference across nearly every major silicon architecture.
llama.cpp Releases
Models & Labsmodels
llama.cpp adds Kimi K3.1-Pro support
Kimi’s new K3.1-Pro model joins the llama.cpp ecosystem, bringing a distinct architectural twist to local inference. By replacing full-attention MLA layers with DSA (Dynamic Sparse Attention) and linear-attention KDA layers, this release tests how well sparse caching handles hybrid attention patterns. The implementation keeps indexer precision high to avoid quality loss during top-k selection, ensuring the model runs accurately on consumer hardware. This expands the library’s reach into newer Chinese open-weight models that rely on complex memory management.
llama.cpp Releases
Models & Labsother
llama.cpp b12182 release with CUDA 13 and ROCm 10
This release quietly cements llama.cpp as the universal inference runtime by adding default builds for CUDA 13.5 and ROCm 10.0 across Linux and Windows. The inclusion of ROCm 10 means AMD GPU users no longer need custom compilation to access modern acceleration, effectively closing the gap with NVIDIA's ecosystem support. While KleidiAI on Apple Silicon is disabled in this build, the broader platform coverage ensures that local inference remains accessible on virtually any hardware configuration without manual setup.
llama.cpp Releases