---
license: cc-by-4.0
language:
- en

tags:
- mlx
- apple-silicon
- text-to-speech
- speech
- speech-generation
- tts
- mlx-audio
- on-device 
- offline
- openvox


extra_gated_prompt: "Prohibited use: Use of our model must comply with all applicable laws and regulations and must not result in, involve, or facilitate any illegal, harmful, deceptive, fraudulent, or unauthorized activity. Prohibited uses include, without limitation, voice impersonation or cloning without explicit and lawful consent; misinformation, disinformation, or deception (including fake news, fraudulent calls, or presenting generated content as genuine recordings of real people or events); and the generation of unlawful, harmful, libelous, abusive, harassing, discriminatory, hateful, or privacy-invasive content. We disclaim all liability for any non-compliant use."
extra_gated_fields:
  Company or university if applicable: text
  I want to use this model for:
    type: select
    options:
      - Work
      - Studies
      - Fun
library_name: pocket-tts
---

# OpenVox TTS — by The Oracle Guy

A lightweight, CPU-friendly text-to-speech model integrated into [OpenVox](https://openvoxai.com), the local AI voice synthesis app for macOS and Windows. Built for developers and creators who want fast, private TTS without cloud APIs or GPU requirements.

[🔊 Try OpenVox](https://openvoxai.com) |
[🤗 Hugging Face](https://huggingface.co/theoracleguy) |
[▶️ YouTube](https://www.youtube.com/@TheOracleGuy_AI)

---

## What this model powers

This model is the TTS backbone used in **OpenVox**, which provides:

- Local, offline text-to-speech — no internet required after install
- Voice cloning from a short audio sample
- 600+ language support via OmniVoice engine
- Audiobook generation from EPUB/PDF
- Multi-speaker Conversations mode (up to 4 voices)
- OpenAI-compatible local API
- macOS (Mac App Store) and Windows apps

---

## Main takeaways

- Runs entirely on CPU — no GPU needed
- Small model footprint (~100M parameters)
- Audio streaming with ~200ms latency to first chunk
- ~6x real-time speed on Apple Silicon (M-series)
- Uses only 2 CPU cores
- Python API and CLI available
- Voice cloning via short audio prompt
- English-first, with multilingual support in OpenVox via OmniVoice
- Can handle arbitrarily long text inputs
- Can run client-side in the browser (WebAssembly)

---

## Try it without installing anything

Visit [openvoxai.com](https://openvoxai.com) to try OpenVox directly, or use the Kyutai demo at [kyutai.org/pocket-tts](https://kyutai.org/pocket-tts) to test the underlying model in your browser.

---

## CLI usage

### Generate audio

```bash
uvx pocket-tts generate
# or after pip install:
pocket-tts generate
```

Modify voice and text:

```bash
pocket-tts generate --voice alba --text "Hello from OpenVox."
```

Available built-in voices: `alba`, `marius`, `javert`, `jean`, `fantine`, `cosette`, `eponine`, `azelma`

The `--voice` argument also accepts a local `.wav` file for voice cloning.

### Run a local server

```bash
pocket-tts serve
```

Navigate to `http://localhost:8000` for the web UI. The model stays in memory between requests, so it's faster for iterating on voices and prompts.

### Export a voice embedding

Processing audio for voice cloning is slow. Use `export-voice` to convert an audio file to a fast-loading `.safetensors` embedding:

```bash
pocket-tts export-voice --input my_voice.wav --output my_voice.safetensors
```

---

## Python API

Install:

```bash
pip install pocket-tts
```

Basic usage:

```python
from pocket_tts import TTSModel
import scipy.io.wavfile

tts_model = TTSModel.load_model()
voice_state = tts_model.get_state_for_audio_prompt("alba")
audio = tts_model.generate_audio(voice_state, "Hello from OpenVox.")
scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy())
```

For performance, keep `load_model()` and `get_state_for_audio_prompt()` results in memory — both are slow operations.

### Fast voice loading with safetensors

```python
from pocket_tts import TTSModel, export_model_state, import_model_state

model = TTSModel.load_model()

# Export once
voice_state = model.get_state_for_audio_prompt("alba")
export_model_state(voice_state, "alba.safetensors")

# Load fast on subsequent runs
voice_state = import_model_state("alba.safetensors")
audio = model.generate_audio(voice_state, "Hello from OpenVox.")
```

---

## OpenVox integration

This model is distributed as part of **OpenVox**, available on:

- **macOS** — [Mac App Store](https://apps.apple.com/app/id6758789314)
- **Windows** — [Direct Download](https://openvoxai.com/)

OpenVox wraps this model in a polished native UI with features like audiobook import, multi-speaker scripts, emotion tags via OmniVoice, and a local OpenAI-compatible API endpoint.

Pricing: free tier (5,000 characters/day) + one-time $20 Pro upgrade. No subscriptions.

---

## In-browser implementations

Pocket TTS (the underlying model) is small enough to run in WebAssembly:

- [pocket-tts-onnx-export](https://github.com/KevinAHM/pocket-tts-onnx-export) — ONNX Runtime Web — [demo](https://huggingface.co/spaces/KevinAHM/pocket-tts-web)
- [pocket-tts (Candle/Rust)](https://github.com/babybirdprd/pocket-tts) — WebAssembly + PyO3
- [jax-js](https://github.com/ekzhang/jax-js/tree/main/website/src/routes/tts) — JAX for the web — [demo](https://jax-js.com/tts)

## Alternative backends

- [pocket-tts-mlx](https://github.com/jishnuvenugopal/pocket-tts-mlx) — MLX backend for Apple Silicon
- [pocket-tts (Candle)](https://github.com/babybirdprd/pocket-tts) — Rust/WebAssembly

---

## Unsupported features (contributions welcome)

- Silence/pause injection via text input
- int8 quantization

GPU execution was tested but showed no speedup over CPU at batch size 1 with this model size.

---

## Prohibited use

Use of this model must comply with all applicable laws and regulations. Prohibited uses include voice impersonation or cloning without explicit consent; generating misinformation, fake recordings, or fraudulent content; and producing harmful, discriminatory, or privacy-invasive audio. The Oracle Guy disclaims all liability for non-compliant use.

---

## Credits

Model architecture based on [Pocket TTS by Kyutai](https://huggingface.co/kyutai/pocket-tts) (CC-BY 4.0).
OpenVox app and integrations by [The Oracle Guy](https://openvoxai.com).