Name: Pocket Tts
Author: sherajdev

According to AlphaMoat, as of 2026-09, Pocket Tts has 3,571 downloads and 3 stars — ranked #3,061 of 5,078 AI skills overall, and #281 of 512 in Design & Media.

Installs

323

Downloads

3.6K

Stars

Overall Rank

#3,061

Top 61% overall · Top 55% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	95	2.9K	3	-
SkillHub ↗	323	3.6K	3	—

Platforms count differently and update at different times.

What this skill does

CLI and Python examples select preset voices or a WAV voice sample, adjust speed and save audio, with an optional local server. Setup requires Python, PyTorch and acceptance of the gated model terms; first use can download model or voice assets. Review and pin dependencies in an isolated environment and clone only voices the user has permission to reproduce. Local inference does not eliminate setup downloads.

Profile published 2026-10-27

What you can do with it

Prepare local English narration with a selected voice

When to use it

When English text needs a local speech-generation workflow

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Check model terms and downloaded assets, select a permitted voice and output path, then prepare English narration without unapproved cloning.

Monthly Trend

Downloads3.6K

Stars3

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	3.6K	—	3
2026-08	3.1K	+4.7%	3
2026-07	3.0K	+17.3%	3
2026-06	2.5K	-2.3%	3
2026-05	2.6K	—	3
2026-03	2.3K	—	3

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

3.1 KB · ClawHub v1.0.1

# Pocket TTS Skill

Fully local, offline text-to-speech using Kyutai's Pocket TTS model. Generate high-quality audio from text without any API calls or internet connection. Features 8 built-in voices, voice cloning support, and runs entirely on CPU.

## Features

- 🎯 **Fully local** - No API calls, runs completely offline
- 🚀 **CPU-only** - No GPU required, works on any computer
- ⚡ **Fast generation** - ~2-6x real-time on CPU
- 🎤 **8 built-in voices** - alba, marius, javert, jean, fantine, cosette, eponine, azelma

Show all (122 lines)

- 🎭 **Voice cloning** - Clone any voice from a WAV sample
- 🔊 **Low latency** - ~200ms first audio chunk
- 📚 **Simple Python API** - Easy integration into any project

## Installation

```bash
# 1. Accept the model license on Hugging Face
# https://huggingface.co/kyutai/pocket-tts

# 2. Install the package
pip install pocket-tts

# Or use uv for automatic dependency management
uvx pocket-tts generate "Hello world"
```

## Usage

### CLI

```bash
# Basic usage
pocket-tts "Hello, I am your AI assistant"

# With specific voice
pocket-tts "Hello" --voice alba --output hello.wav

# With custom voice file (voice cloning)
pocket-tts "Hello" --voice-file myvoice.wav --output output.wav

# Adjust speed
pocket-tts "Hello" --speed 1.2

# Start local server
pocket-tts --serve

# List available voices
pocket-tts --list-voices
```

### Python API

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

# Load model
tts_model = TTSModel.load_model()

# Get voice state
voice_state = tts_model.get_state_for_audio_prompt(
    "hf://kyutai/tts-voices/alba-mackenna/casual.wav"
)

# Generate audio
audio = tts_model.generate_audio(voice_state, "Hello world!")

# Save to WAV
scipy.io.wavfile.write("output.wav", tts_model.sample_rate, audio.numpy())

# Check sample rate
print(f"Sample rate: {tts_model.sample_rate} Hz")
```

## Available Voices

| Voice | Description |
|-------|-------------|
| alba | Casual female voice |
| marius | Male voice |
| javert | Clear male voice |
| jean | Natural male voice |
| fantine | Female voice |
| cosette | Female voice |
| eponine | Female voice |
| azelma | Female voice |

Or use `--voice-file /path/to/wav.wav` for custom voice cloning.

## Options

| Option | Description | Default |
|--------|-------------|---------|
| `text` | Text to convert | Required |
| `-o, --output` | Output WAV file | `output.wav` |
| `-v, --voice` | Voice preset | `alba` |
| `-s, --speed` | Speech speed (0.5-2.0) | `1.0` |
| `--voice-file` | Custom WAV for cloning | None |
| `--serve` | Start HTTP server | False |
| `--list-voices` | List all voices | False |

## Requirements

- Python 3.10-3.14
- PyTorch 2.5+ (CPU version works)
- Works on 2 CPU cores

## Notes

- ⚠️ Model is gated - accept license on Hugging Face first
- 🌍 English language only (v1)
- 💾 First run downloads model (~100M parameters)
- 🔊 Audio is returned as 1D torch tensor (PCM data)

## Links

- [Demo](https://kyutai.org/tts)
- [GitHub](https://github.com/kyutai-labs/pocket-tts)
- [Hugging Face](https://huggingface.co/kyutai/pocket-tts)
- [Paper](https://arxiv.org/abs/2509.06926)