ZONOS3-Mini is Zyphra's compact text-to-speech model supporting 43 languages, with about 100 million active parameters per token (800 million total in the backbone).
Alternatives to ZONOS3-Mini-hf
120 open-weight models that do the same job as ZONOS3-Mini-hf (1B TTS), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
Compare ZONOS3-Mini-hf with the top 3Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.
915MApache 2.0857.9K 375Jan 2026- Same category
- Similar size (915M vs 1B)
- Commercial use OK
Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.
906MApache 2.0709.3K 212Jan 2026- Same category
- Similar size (906M vs 1B)
- Commercial use OK
VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation.
1BMIT122.7K 1.3KDec 2025- Same category
- Similar size (1B vs 1B)
- Commercial use OK
OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.
613MUnknown licence4.3M 1.7KMar 2026- Same category
- Similar size (613M vs 1B)
- Widely used
This repository contains Ming-3.0-tts-0.5B, the dense Ming-3.0-tts checkpoint built on Qwen2.5-0.5B. The checkpoint includes the backbone, DiT head, audio tokenizer, speaker encoder and text tokenizer.
1.5BMIT18.6K 234Sept 2026- Same category
- Similar size (1.5B vs 1B)
- Commercial use OK
Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs.
1.9BApache 2.01.1M 2.3KJan 2026- Same category
- Similar size (1.9B vs 1B)
- Commercial use OK
We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control.
1.9BApache 2.0675.7K 487Jan 2026- Same category
- Similar size (1.9B vs 1B)
- Commercial use OK
Indic Parler-TTS is a multilingual Indic extension of Parler-TTS Mini.
938MApache 2.0183K 610Oct 2024- Same category
- Similar size (938M vs 1B)
- Commercial use OK
VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.
2.3BApache 2.0973.2K 1.8KApr 2026- Same category
- Larger (2.3B vs 1B)
- Commercial use OK
This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.
601MApache 2.025.6K 480Oct 2026- Same category
- Similar size (601M vs 1B)
- Commercial use OK
This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.
601MApache 2.025.6K 480Oct 2026- Same category
- Similar size (601M vs 1B)
- Commercial use OK
Dia2 is a streaming dialogue TTS model created by Nari Labs.
1.1BApache 2.02.3K 27Nov 2025- Same category
- Similar size (1.1B vs 1B)
- Commercial use OK
See also the pre-print research paper, the project page, the Colab example, the GitHub repository, and the repository of voices.
1.6BCC BY 4.0133.4K 385Jun 2025- Same category
- Similar size (1.6B vs 1B)
- Commercial use OK
Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages.
500MMIT2.7M 1.9KApr 2025- Same category
- Smaller (500M vs 1B)
- Commercial use OK
- Widely used
Key Improvements: - 🔊 Higher Quality: 44.1kHz sampling rate preserves more high-frequency details for better voice cloning - ⚡ More Efficient: Reduced token rate (6.25Hz) lowers computational cost while maintaining performance - 🎓 Fine-tuning Support: Train personalized voice models with SFT or…
802MApache 2.06K 364Dec 2025- Same category
- Similar size (802M vs 1B)
- Commercial use OK
Sarashina2.2-TTS is a Japanese-centric text-to-speech system built on a large language model, developed by SB Intuitions. It supports Japanese and English, delivering high pronunciation accuracy, naturalness, and stability across diverse speaking styles, with zero-shot voice generation support.
810M8K ctx Unknown licence2.1K 76Apr 2026- Same category
- Similar size (810M vs 1B)
Ming-omni-tts is a high-performance unified audio generation model that achieves precise control over speech attributes and enables single-channel synthesis of speech, environmental sounds, and music.
1.6BApache 2.011.8K 43Feb 2026- Same category
- Similar size (1.6B vs 1B)
- Commercial use OK
Parler-TTS Mini Multilingual v1.1 is a multilingual extension of Parler-TTS Mini.
938MApache 2.012.2K 61Nov 2024- Same category
- Similar size (938M vs 1B)
- Commercial use OK
Fun-CosyVoice 3.0 is an advanced text-to-speech (TTS) system based on large language models (LLM), surpassing its predecessor (CosyVoice 2.0) in content consistency, speaker similarity, and prosody naturalness. It is designed for zero-shot multilingual speech synthesis in the wild.
500MApache 2.0142.2K 692Dec 2025- Same category
- Smaller (500M vs 1B)
- Commercial use OK
Gepard is a text-to-speech model built for real-time conversation. It starts speaking the moment text begins arriving, generating audio piece by piece instead of waiting for a full sentence — so it feels like a live voice, not a recording.
556M256K ctx Apache 2.012.7K 134Jun 2026- Same category
- Similar size (556M vs 1B)
- Commercial use OK
Audio8 TTS Preview supports multilingual speech generation and zero-shot voice cloning. This repository contains the complete checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and Hugging Face remote code.
601MApache 2.03.8K 435Jul 2026- Same category
- Similar size (601M vs 1B)
- Commercial use OK
Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.
1.6BApache 2.024.9K 135Jun 2025- Same category
- Similar size (1.6B vs 1B)
- Commercial use OK
Parler-TTS Mini v1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).
878MApache 2.031.2K 153Jun 2024- Same category
- Similar size (878M vs 1B)
- Commercial use OK
Parler-TTS Mini v1.1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).
938MApache 2.05.7K 30Oct 2024- Same category
- Similar size (938M vs 1B)
- Commercial use OK