Tasks and inputs
ZONOS3-Mini is listed for Audio, Text-to-speech. It accepts text, audio and produces audio. Use the publisher’s input format and preprocessing for your chosen deployment.
ZONOS3-Mini is Zyphra's open multilingual text-to-speech model: 800M MoE with ~100M active, zero-shot voice cloning in 43 languages and 80 ms first audio.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Under 570 ms to first audio in a phone's browser. Under 150 ms on a MacBook Air. About 80 ms on a server GPU. ZONOS3-Mini, released by Zyphra on 12 November 2026, is a text-to-speech model built to run wherever your users are, and it clones a voice from up to a minute of reference audio in 43 languages.
Weights are Apache-2.0; the runtimes and reference code are MIT.
It stores about 800M parameters but activates roughly 100M per token. Eleven layers combine nine Gated DeltaNet blocks with two global attention blocks, feeding a 64-expert latent mixture-of-experts with top-2 routing. Audio is decoded through Zyphra's ZAC-1 codec at 15 Hz to 44.1 kHz output. The 32,768-position context covers about ten minutes of continuous speech.
The Hub lists 0.9B parameters against the 800M quoted in the release text. A rounding difference, most likely, but size memory for the larger figure. The release text also dates itself a day earlier than its publication date.
| Runtime | Notes |
|---|---|
| SGLang-Omni | OpenAI-compatible streaming /v1/audio/speech; sgl-omni serve --model-path Zyphra/ZONOS3-Mini |
| MLX | Apple Silicon |
| C++ / ggml | CPU, CUDA, Metal and Vulkan with quantised GGUF weights |
| WebGPU | In-browser Voice Studio |
On a single H100 at concurrency 8 the median time to first audio is 80 ms, with peak throughput of 457x real time. Zyphra's figures.
This is the reason to choose it over a plain voice model:
Cloning works from an in-context reference of up to 60 seconds, or from a single speaker embedding.
Voice cloning raises consent questions that are yours to answer, not the model's. Build your pipeline so that reference audio comes only from speakers who agreed, and log it.
Write 40 lines your product actually says, including numbers, names and a few emotional reads. Generate them in your top three languages on the runtime you would ship, browser included if relevant. Score naturalness with listeners and time to first audio on real devices. Compare with Voxtral TTS and Gemini 3.8 Flash TTS, or browse text-to-speech models.
Compare the model on the work you need to complete.
ZONOS3-Mini is listed for Audio, Text-to-speech. It accepts text, audio and produces audio. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 32.77K context. Compare pronunciation, voice consistency and time to the first playable audio. Check the service’s billing unit for the actual script.
The weights are downloadable under Apache-2.0 (weights); MIT (runtimes). Check runtime support and size the complete model and working context for your expected concurrency.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Alibaba
Qwen-Audio-3.1-TTS Plus is Alibaba's premium text-to-speech model for brand voices and dubbing, with fine-grained emotion tags and noise-robust voice cloning.
Mistral AI
Voxtral TTS 3 is Mistral's speech synthesis model for batch and streaming audio, with voice cloning, emotion tags and 35+ languages at $13 per 1M chars.
fish-audio
Fish Audio Drama 3 is an expressive 35B MoE text-to-speech model steered by bracketed directions, covering 83 languages, with downloadable weights.
heygen
HeyGen Voice is HeyGen's default text-to-speech model: about 39 languages, public and cloned voices, streaming with character timestamps.
heygen
HeyGen Voice Turbo is the low-latency version of HeyGen's TTS model for public voices and instant clones, at $4 per 1M characters.
Alibaba
Qwen-Audio-3.1-TTS Flash is Alibaba's streaming text-to-speech model for voice assistants, live chat and customer service, with system and cloned voices.