Zyphra releases ZONOS3-Mini, an Apache 2.0 TTS model with 100M active parameters
Zyphra released ZONOS3-Mini, an Apache 2.0 text-to-speech model with 800M total parameters and 100M active parameters. It clones voices, steers delivery word by word and runs in real time in the browser.
Zyphra has released ZONOS3-Mini, an Apache 2.0 text-to-speech model with 800M total parameters and 100M active parameters, according to a MarkTechPost report published November 10, 2026.
Key specifications
- Developer: Zyphra
- Model: ZONOS3-Mini
- License: Apache 2.0
- Total parameters: 800M
- Active parameters: 100M
- Pricing: not yet disclosed
- Context window: not applicable to the reported details
Capabilities
According to the report, ZONOS3-Mini does three things:
- Voice cloning: the model clones voices.
- Word-by-word steering: users can steer delivery at the level of individual words.
- Real-time browser inference: the model runs in real time in the browser.
The gap between 800M total and 100M active parameters indicates a design in which only part of the model's weights is used for each step of generation. The report presents the 100M active figure as the headline size of the model.
What this means
The Apache 2.0 license is a permissive open-source license, so the model's release terms are settled by the license itself. Running in real time in the browser is a stated capability that ties directly to the 100M active parameter count, which is the figure Zyphra's release is framed around. Benchmark scores for ZONOS3-Mini were not part of the report, so quality comparisons against other TTS models await published evaluations.
Related Articles
Underdog Woof, a 40.6 MB two-voice TTS model, claims 1.42% word error rate on a CPU
Underdog Woof is an English text-to-speech model with two voices, Juno and Mira, packaged as a single 40.6 MB file that runs on a CPU with numpy. Underdog reports a 1.42% word error rate for Mira on Gradium TTS Hard Cases, against 1.89% for Fish Audio Drama 3, a 41.5 GB download.
Tencent releases Hy4: 770B total parameters, 49B active, with native vision and computer use
Tencent has released Hy4, with 770B total parameters and 49B active parameters. It is the first Hy model with native vision and computer-use support. Weights are due to be open-sourced soon, and a lower-cost Hy4 flash is coming.
Google rolls out Gemini 4 Carbon to AI Ultra subscribers at $2/$10 per 1M tokens, Argon stays
Google is rolling out Gemini 4 Carbon to AI Ultra subscribers in the Gemini app, AI Mode and Antigravity, following last month's preview. Introductory API pricing is $2 per 1M input tokens and $10 per 1M output tokens until November 30, and Argon remains available for AI Pro and up.
NVIDIA Alpamayo 2 Edge: 2B-Parameter Driving Model Hits 160-190 ms Latency on DRIVE AGX Thor
NVIDIA has introduced Alpamayo 2 Edge, a 2B-parameter adaptive reasoning vision-language-action model built for real-time operation on DRIVE AGX Thor. NVIDIA says deployment recipes with TensorRT and DFlash2 reach 160-190 ms pixel-to-trajectory latency, and that closed-loop RL improved driving performance by 48.9%.
Comments
Loading...