# TeraTTSv2

> If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!

- **Organisation:** TeraSpace
- **Category:** Text-to-Speech
- **Licence:** terattsv2-openrail-m-commercial-attribution (Commercial use with conditions)
- **Released:** 2026-08-07
- **Hugging Face:** 3.8K downloads (30 days), 40 likes

## Runs with

- [ONNX Runtime](https://onnxruntime.ai)
- [Transformers](https://github.com/huggingface/transformers)

## About

If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!

---

TeraTTSv2 is a self-contained ONNX Runtime text-to-speech release with selectable diffusion samplers, ten voice styles, Russian stress marking, and streamed audio output.

This release uses the clean English/Russian 25-second teacher and its matching eight-step CFG-3 distilled student.

Important — Russian stress is automatic. Text inside … receives stress markers automatically by default. Explicit + markers always win. Important — cross-language prompts. When an English reference voice is speaking Russian, experiment with duration_scale below 1 (for example 0.8). It is usually a better starting point than the default 1. Recommended voices: ru_f1 and ru_m5 are the preferred Russian voice prompts.

## Alternatives

- [k2-fsa/OmniVoice](https://selfhost.directory/models/k2-fsa/omnivoice) (613M, Unknown licence, ≈1.87 GB): 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.
- [openbmb/VoxCPM2](https://selfhost.directory/models/openbmb/voxcpm2) (2.3B, Apache 2.0, ≈5.62 GB): 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.
- [Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice](https://selfhost.directory/models/qwen/qwen3-tts-12hz-1.7b-customvoice) (1.9B, Apache 2.0, ≈4.78 GB): 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.
- [Qwen/Qwen3-TTS-12Hz-0.6B-Base](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-base) (915M, Apache 2.0, ≈2.54 GB): Qwen3-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.
- [hexgrad/Kokoro-82M](https://selfhost.directory/models/hexgrad/kokoro-82m) (82M, Apache 2.0, ≈0.68 GB): 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.
- [Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice](https://selfhost.directory/models/qwen/qwen3-tts-12hz-0.6b-customvoice) (906M, Apache 2.0, ≈2.52 GB): Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.

More: https://selfhost.directory/models/teraspace/terattsv2/alternatives

## FAQ

**Can I use TeraTTSv2 commercially?**
Yes, with conditions. It is released under terattsv2-openrail-m-commercial-attribution. Custom licence: read the model card before using it commercially.

**How do I run TeraTTSv2 locally?**
It runs with Transformers. Each has copy-paste examples in its docs.

## Links

- huggingface: https://huggingface.co/TeraSpace/TeraTTSv2

---
Source: https://selfhost.directory/models/teraspace/terattsv2