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.
Alternatives to Audio8-TTS-Realistic-Air
120 open-weight models that do the same job as Audio8-TTS-Realistic-Air (601M 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.
Dia2 is a streaming dialogue TTS model created by Nari Labs.
1.9BApache 2.06K 189Nov 2025- Same category
- Larger (1.9B vs 601M)
- 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…
2.1BApache 2.07.2K 53Feb 2026- Same category
- Larger (2.1B vs 601M)
- Commercial use OK
VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking.
2.7BMIT214.9K 2.5KAug 2025- Same category
- Larger (2.7B vs 601M)
- Commercial use OK
State-of-the-art Voice AI has been locked behind web APIs for too long. The NeuTTS Nano Multilingual Collection is a collection of super-fast, highly realistic, on-device TTS speech language models with instant voice cloning - built to run smoothly on CPUs and edge devices.
229MCustom licence974 81Nov 2025- Same category
- Smaller (229M vs 601M)
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.
?BOpenRAIL81.6K 1.1KMay 2026- Same category
Parler-TTS Mini Multilingual v1 is a multilingual extension of Parler-TTS Mini.
938MApache 2.0171 28Oct 2024- Same category
- Similar size (938M vs 601M)
- 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 2.04.8K 2.9KApr 2025- Same category
- Larger (1.6B vs 601M)
- 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…
3.1BApache 2.0160.4K 32Feb 2026- Same category
- Larger (3.1B vs 601M)
- Commercial use OK
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-license32K 279Aug 2026- Same category
Audio8 TTS 0.1B supports speech generation and zero-shot voice cloning. This repository contains the complete v4 mixed checkpoint, its neural audio codec, tokenizer, processor, and Hugging Face remote code.
170Maudio8-community-license-v1.01.3K 248Aug 2026- Same category
- Smaller (170M vs 601M)
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…
2.3BApache 2.011.6K 122Feb 2026- Same category
- Larger (2.3B vs 601M)
- Commercial use OK
State-of-the-art Voice AI has been locked behind web APIs for too long. The NeuTTS Nano Multilingual Collection is a collection of super-fast, highly realistic, on-device TTS speech language models with instant voice cloning - built to run smoothly on CPUs and edge devices.
229MCustom licence283 27Feb 2026- Same category
- Smaller (229M vs 601M)
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 4.0111 304Nov 2024- Same category
- Similar size (362M vs 601M)
- Commercial use OK
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 4.018.3K 268May 2026- Same category
- Commercial use OK
MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities: Emotional speech rhythm and tone in English. No hallucinations. Support for voice cloning with finetuning.
1BApache 2.0497 787Feb 2024- Same category
- Similar size (1B vs 601M)
- 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 2.0122.1K 253Apr 2026- Same category
- Smaller (100M vs 601M)
- Commercial use OK
Breeze TTS 2 is an open-weight text-to-speech model built for real-time interaction. It ranks #1 among open-weight models on the Artificial Analysis TTS leaderboard, while outperforming frontier proprietary systems.
3.5Bbreezeblue-research-and-non-commercial-license27.1K 1KAug 2026- Same category
- Larger (3.5B vs 601M)
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.
?BMIT8K 55Aug 2026- Same category
- Commercial use OK
Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient.
82MApache 2.013.3M 7.5KDec 2024- Same category
- Smaller (82M vs 601M)
- Commercial use OK
- Widely used
YuE2 is an open music generation model with frontier song quality competitive with Suno v5/v6. Turn lyrics and a style prompt into a complete song with vocals and accompaniment, then shape its melody and chords through an editable score.
3.6B24K ctx CC BY-NC 4.020.2K 1.3KSept 2026- Same category
- Larger (3.6B vs 601M)
If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!
?Bterattsv2-openrail-m-commercial-attribution3.8K 40Aug 2026- Same category
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.
1.7BApache 2.01K 1.1KFeb 2025- Same category
- Larger (1.7B vs 601M)
- Commercial use OK
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 33Jul 2026- Same category
- Smaller (82M vs 601M)
Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI.
350MMIT0 720Dec 2025- Same category
- Similar size (350M vs 601M)
- Commercial use OK