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.
Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.
82MOpenRAIL72.7K 32Jul 2026- Same category
- Smaller (82M vs 1B)
OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a…
362M4K ctx CC BY 4.095 304Nov 2024- Same category
- Smaller (362M vs 1B)
- Commercial use OK
MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving…
100M32K ctx Apache 2.0123.1K 253Apr 2026- Same category
- Smaller (100M vs 1B)
- Commercial use OK
GLM-TTS is a high-quality text-to-speech (TTS) synthesis system based on large language models, supporting zero-shot voice cloning and streaming inference. The system adopts a two-stage architecture combining an LLM for speech token generation and a Flow Matching model for waveform synthesis.
?BMIT639 352Dec 2025- Same category
- Commercial use OK
This repository contains Ming-3.0-tts-tiny, the Ming-3.0-tts mixture-of-experts checkpoint built on Ling V3. Its Ling V3 backbone has 7.9B total parameters and activates about 1.3B parameters per token.
9BA2.5BMIT9.4K 61Sept 2026- Same category
- Larger (9B vs 1B)
- Commercial use OK
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
?BMIT75.9K 47Feb 2024- Same category
- Commercial use OK
Irodori-TTS-v4-Large is a Japanese Text-to-Speech model based on a Rectified Flow Diffusion Transformer (RF-DiT) architecture. It combines Text (Input) + Reference Speech + Caption Text in a unified model, enabling zero-shot voice cloning, text-based voice design, and style-controlled voice cloning.
3.3BGemma Terms of Use0 94Sept 2026- Same category
- Larger (3.3B vs 1B)
4/9/2025 – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS
3.3BApache 2.055 26Apr 2025- Same category
- Larger (3.3B vs 1B)
- Commercial use OK
FishAudio S1 is a leading text-to-speech (TTS) model trained on more than 2 million hours of audio data in multiple languages.
?BCC BY-NC-SA 4.02.2K 806May 2025- Same category
\[!TIP] \[IMPORTANT] For security issues, we do not upload the parameters of WaveVAE encoder to the above links. You can only use the pre-extracted latents from link1 for inference. If you want to synthesize speech for speaker A, you need "A.wav" and "A.npy" in the same directory.
?BApache 2.02.7K 421Mar 2025- Same category
- Commercial use OK
Ming-3.0-audio-tiny is a compact native audio-language model from inclusionAI. It accepts audio together with text instructions and supports speech recognition, spoken question answering, audio understanding, audio reasoning, and optional synthesized-speech responses.
8.9BA2.1BMIT5.1K 64Sept 2026- Same category
- Larger (8.9B vs 1B)
- Commercial use OK
Fish Speech V1.5 is a leading text-to-speech (TTS) model trained on more than 1 million hours of audio data in multiple languages.
?BCC BY-NC-SA 4.05.2K 788Nov 2024- Same category
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…
8.4BApache 2.011.3K 64Feb 2026- Same category
- Larger (8.4B vs 1B)
- Commercial use OK
Türkçe özet. Antalia-2 Mini, tek sesli, küçük bir Türkçe metinden konuşmaya (TTS) modelidir: toplam 7,6 milyon parametre, 48 kHz çıkış, sıradan bir işlemcide gerçek zamandan çok daha hızlı.
8MApache 2.012.2K 56Oct 2026- Same category
- Smaller (8M vs 1B)
- Commercial use OK
🎬 Fun-CineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes
?BApache 2.0109 63Mar 2026- Same category
- Commercial use OK
tiny-voca is a small English text-to-speech model with two voices, F2 (female) and M2 (male). The complete model, including the waveform generator, has 4.5M parameters and was trained from scratch on about 18 hours of synthetic speech. It runs about 70x faster than real time on four CPU threads.
5MApache 2.07.9K 388Nov 2026- Same category
- Smaller (5M vs 1B)
- Commercial use OK
- Newer release
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
?BMIT25.1K 108Feb 2024- Same category
- Commercial use OK
82M parameters, 16 languages, 118 voices, 24 kHz. ONNX with int8 weights (82.7 MB; runs on CPU, no PyTorch needed), and the float32 PyTorch weights.
82MApache 2.06.4K 73Nov 2026- Same category
- Smaller (82M vs 1B)
- Commercial use OK
- Newer release
Our model, Llasa, is a text-to-speech (TTS) system that extends the text-based LLaMA (1B,3B, and 8B) language model by incorporating speech tokens from the XCodec2 codebook, which contains 65,536 tokens. We trained Llasa on a dataset comprising 250,000 hours of Chinese-English speech data.
4B128K ctx CC BY-NC 4.0187 531Jan 2025- Same category
- Larger (4B vs 1B)
Underdog Woof is a small English text-to-speech model with two voices: Juno and Mira. It reads phone numbers, dates, prices and codes the way people say them, and it runs on a laptop CPU with nothing but numpy, from a single 40.6 MB file. Try it in your browser at underdog.ai/woof.
?Bunderdog-non-commercial-1.010 287Nov 2026- Same category
We are also training larger-scale models and need computational power and data support. If you can provide assistance, please contact OPEN-SOURCE@2NOISE.COM. Thank you very much.
?BCC BY-NC 4.08.2K 1.7KMay 2024- Same category
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include:
?BMIT13.3K 30Feb 2024- Same category
- Commercial use OK
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…
8.5BApache 2.04.8K 444Feb 2026- Same category
- Larger (8.5B vs 1B)
- Commercial use OK
Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI.
350MMIT0 720Dec 2025- Same category
- Smaller (350M vs 1B)
- Commercial use OK