---
license: other
license_name: terattsv2-openrail-m-commercial-attribution
license_link: https://huggingface.co/TeraSpace/TeraTTSv2/blob/main/LICENSE
library_name: transformers
pipeline_tag: text-to-speech
tags:
- onnxruntime
- text-to-speech
- russian
- english
- custom-code
---

## 💜 Support TeraTTSv2

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

| Currency | Donation address |
| :--- | :--- |
| **ETH** | `0x19766c207F82303c3998976d852DB82e8Dcc5d77` |
| **GRAM (TON)** | `UQDYx1blVO8H31APnRUXVg2uTXV--wXX8HdTyKxnOKQciPQj` |
| **SOL** | `DvBjAqaj4AYWi3JBMcW4FmXsaU4Nu6yjxrox4XJZ6o6Z` |
| **Tether USDt (TRON / TRC20)** | `TZ6QeYZSr2h22rzGqQZQZTMzWYVPdUej1y` |
| **BTC** | `bc1q2l0xdlylqpweu4sm3y53f95g0nazcm8yu42gkq` |

---

# TeraTTSv2 ONNX

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 `<ru>…</ru>` 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.

## Model license

**The model weights are free to use, including in commercial applications, under
Open RAIL-M with an additional commercial attribution condition.** See the full
[TeraTTSv2 Model License](LICENSE) and the accompanying
[BigScience Open RAIL-M License](LICENSE-OPENRAIL), including its use-based
restrictions.

If you use TeraTTSv2, or a modified, fine-tuned, quantized, converted, or distilled
version, in a commercial product or service, **clearly mention TeraTTSv2 by
TeraSpace in the product's public description**, such as its official product page
or app-store listing. Link to this model wherever hyperlinks are supported.
This applies to local applications and products that use the model on a backend.

Example credit:

> Text-to-speech powered by [TeraTTSv2 by TeraSpace](https://huggingface.co/TeraSpace/TeraTTSv2).

For a derivative, use "Text-to-speech based on TeraTTSv2 by TeraSpace."

There are no model licensing fees or royalties payable to TeraSpace. Donations
are optional. You may keep your application code private. When redistributing
the model or a derivative, include both license files, retain the commercial
attribution condition, preserve upstream notices, identify modifications, and
pass on the upstream use restrictions as required by the full license terms.

The model license preserves the upstream Supertonic terms. Separately licensed
components retain their own licenses; see [RUACCENT_NOTICE.txt](RUACCENT_NOTICE.txt)
for the RUAccent components.

## Installation

```bash
pip install -r requirements.txt
```

`sounddevice` is only required for direct speaker playback. On Linux, install
the system PortAudio library if it is not already present.

## Load with Transformers

```python
from transformers import AutoModel

tts = AutoModel.from_pretrained(
    "TeraSpace/TeraTTSv2",
    trust_remote_code=True,
    provider="CPUExecutionProvider",
    threads=6
)

waveform = tts.generate_speech(
    "<ru>Привет от TeraTTS.</ru>",
    voice="ru_f1",
    duration_scale=1,
)
tts.save_wav("teratts.wav", waveform)
```

`waveform` is a mono `float32` NumPy array at 44,100 Hz. `save_wav` writes
standard signed-16-bit PCM WAV without an extra audio package.

To inspect the exact text passed to the encoder after number expansion, stress
marking, and Unicode normalization, call `tts.normalize_text(text)`.

## Controls

| Control | Values | Effect |
| --- | --- | --- |
| `voice` | `ru_f1` ★, `ru_m5` ★, `ru_f2`, `ru_m1`, `eng_f3`, `eng_f4_whisper`, `eng_f5`, `eng_m2_whisper`, `eng_m3`, `eng_m4` | Selects a bundled precomputed voice style named after its reference audio. ★ marks the recommended Russian prompts. |
| `duration_scale` | Positive float, default `1` | Higher values produce slower, longer speech. |
| `diffusion_model` | `distilled` (default), `teacher` | Distilled is faster; teacher supports adjustable CFG. |
| `ruaccent_mode` | `full` (default), `dictionary` | Full uses RUAccent neural ONNX graphs plus dictionaries; dictionary mode loads dictionaries only. |

The default `diffusion_model="distilled"` is the fast eight-step sampler. To
use the teacher sampler, choose it while loading:

```python
teacher_tts = AutoModel.from_pretrained(
    "TeraSpace/TeraTTSv2",
    trust_remote_code=True,
    provider="CPUExecutionProvider",
    threads=6,
    diffusion_model="teacher",
)
```

`guidance` can be adjusted when generating with the teacher sampler. The
distilled sampler has CFG 3 baked into its graph.

## Language tags, numbers, and Russian stress

Language tags are required: wrap text in `<en>…</en>` or `<ru>…</ru>`. The
runtime rejects untagged or unbalanced input with a tag-specific error. Before
number expansion and stress marking, it inserts spaces after punctuation and
between a number and a following word. Characters outside the model vocabulary
are skipped with a runtime warning. Numbers inside language tags are expanded to
words in the matching language before synthesis:

```python
waveform = tts.generate_speech(
    "<ru>У меня 21 яблоко.</ru> <en>I have 42 apples.</en>",
    voice="ru_f1",
    duration_scale=1,
)
```

Russian text is automatically stress-marked by the bundled RUAccent-derived
runtime. Manual `+` markers remain authoritative. For a lower-memory,
deterministic dictionary-only path, choose the mode while loading:

```python
dictionary_tts = AutoModel.from_pretrained(
    "TeraSpace/TeraTTSv2",
    trust_remote_code=True,
    provider="CPUExecutionProvider",
    threads=6,
    ruaccent_mode="dictionary",
)
```

Dictionary mode does not load RUAccent neural ONNX graphs. It marks known
words and applies deterministic `ё` replacements, while unknown words and
ambiguous homographs are left unchanged. Set `russian_stress=False` to disable
automatic Russian stress processing entirely.

When using an English voice such as `eng_f3` for Russian text, start by trying
`duration_scale=0.8` and adjust by ear:

```python
waveform = tts.generate_speech(
    "<ru>Это русский текст английским голосом.</ru>",
    voice="eng_f3",
    duration_scale=0.8,
)
```

## Stream audio

```python
for chunk in tts.generate_speech_stream(
    "<en>Streaming speech is ready.</en>",
    voice="eng_f3",
    duration_scale=1,
):
    # Send float32 mono chunks (44,100 Hz) to a player or network client.
    consume(chunk)
```

The remote code loads only the selected sampler graph plus shared ONNX graphs.
For security, pin a specific Hub commit when using `trust_remote_code=True`.

## Attribution

The local Russian stress annotator and its assets are adapted from
[RUAccent](https://github.com/Den4ikAI/ruaccent), Copyright 2026 Denis Petrov,
under the MIT License. See `RUACCENT_NOTICE.txt`.