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.
Irodori-TTS-v4-Small 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.
766MMIT0 55Aug 2026- Same category
- Similar size (766M vs 1B)
- Commercial use OK
This checkpoint is a minor update to Irodori-TTS-v4-Small with an improved duration predictor.
766MMIT0 77Aug 2026- Same category
- Similar size (766M vs 1B)
- Commercial use OK
We release IndicF5, a near-human polyglot Text-to-Speech (TTS) model trained on 1417 hours of high-quality speech from Rasa, IndicTTS, LIMMITS, and IndicVoices-R.
351MMIT40.4K 474Mar 2025- Same category
- Smaller (351M vs 1B)
- Commercial use OK
Parler-TTS Mini v0.1 is a lightweight text-to-speech (TTS) model, trained on 10.5K 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).
647MApache 2.01.9K 359Apr 2024- Same category
- Similar size (647M vs 1B)
- Commercial use OK
Maya-1 is an open-weight text-to-speech model from Maya Research that combines natural-language voice descriptions with inline expressive controls. It generates speech as discrete audio tokens, which are decoded into a 24 kHz waveform.
3.3B128K ctx Apache 2.08.3K 946Oct 2025- Same category
- Larger (3.3B vs 1B)
- Commercial use OK
rumik-oss 1 is a 3b multilingual text-to-speech model from rumik ai, trained on fewer than 70,000 hours of speech while performing competitively with existing TTS models. it combines code-switched synthesis, description-conditioned delivery, and inline vocalization control, with 24 khz audio output.
3.4B8K ctx CC BY-NC 4.0900 68Sept 2026- Same category
- Larger (3.4B vs 1B)
MiDashengLM-Gen is an end-to-end framework that uses a pre-trained Large Language Model and audio tokenizer as the backbone, combined with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation.
2.9BApache 2.0240 47Aug 2026- Same category
- Larger (2.9B vs 1B)
- Commercial use OK
Fish Audio S2 Pro is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture.
4.6Bfish-audio-research-license43K 1.5KMar 2026- Same category
- Larger (4.6B vs 1B)
Parler-TTS Mini: Expresso is a fine-tuned version of Parler-TTS Mini v0.1 on the Expresso dataset. It is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech.
647MApache 2.0789 117May 2024- Same category
- Similar size (647M vs 1B)
- Commercial use OK
Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.
?BOpenRAIL84.4K 1KMay 2026- Same category
MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English. It can transform dialogue scripts between two speakers into natural, expressive conversational speech.
2B32K ctx Apache 2.0175 54Jul 2025- Same category
- Similar size (2B vs 1B)
- Commercial use OK
Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations
370M125K ctx lfm1.0786 183Feb 2026- Same category
- Smaller (370M vs 1B)
IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports Chinese, English, Japanese, Spanish and Arabic, with cross-lingual voice transfer and emotion control disentangled from timbre.
?Bbilibili-model-license31.5K 276Aug 2026- Same category
Parler-TTS Large v1 is a 2.2B-parameters 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).
2.3BApache 2.04.6K 278Aug 2024- Same category
- Larger (2.3B vs 1B)
- Commercial use OK
03/18/2025 – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS
3.8B128K ctx Apache 2.049K 765Mar 2025- Same category
- Larger (3.8B vs 1B)
- Commercial use OK
Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations
370M125K ctx lfm1.0306 43Feb 2026- Same category
- Smaller (370M vs 1B)
Magenta RealTime 2 is offered under a combination of licenses: the codebase is licensed under Apache 2.0, and the model weights under Creative Commons Attribution 4.0 International. In addition, we specify the following usage terms:
?BCC BY 4.018.4K 267May 2026- Same category
- Commercial use OK
The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model, and it runs faster than real time on a laptop CPU.
?BMIT7.8K 55Aug 2026- Same category
- Commercial use OK
MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English. It can transform dialogue scripts between two speakers into natural, expressive conversational speech.
2BApache 2.041 28Jun 2025- Same category
- Similar size (2B vs 1B)
- Commercial use OK
A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.
370M125K ctx lfm1.0311 165Sept 2025- Same category
- Smaller (370M vs 1B)
Marvis is a cutting-edge conversational speech model designed to enable real-time streaming text-to-speech synthesis. Built with efficiency and accessibility in mind, Marvis addresses the growing need for high-quality, real-time voice synthesis that can run on consumer devices such as Apple…
368MApache 2.0249 29Oct 2025- Same category
- Smaller (368M vs 1B)
- Commercial use OK
Voxtral TTS is a frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents. The model is released with BF16 weights and a set of reference voices.
4BCC BY-NC 4.02.7K 957Nov 2025- Same category
- Larger (4B vs 1B)
If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!
?Bterattsv2-openrail-m-commercial-attribution3.9K 37Aug 2026- Same category
OuteTTS-0.2-500M is our improved successor to the v0.1 release. The model maintains the same approach of using audio prompts without architectural changes to the foundation model itself.
499M32K ctx CC BY-NC 4.0154 314Nov 2024- Same category
- Smaller (499M vs 1B)