Skip to content
TakoAPI
Back to skills

lb-pocket-tts-skill

by leonaaardob

Media & Streaming
729Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Generate speech from text using Kyutai Pocket TTS - lightweight, CPU-friendly, streaming TTS with voice cloning.

Description

What This Skill Does

Pocket-TTS generates speech from text using the Kyutai model locally on CPU, with no GPU required. It supports voice cloning from short audio samples and streaming output with under 200ms latency. English only, approximately 6x faster than real-time on modern hardware.

Runs entirely on CPU without cloud API dependencies, making it faster to set up and cheaper to operate than hosted TTS services for local or offline workflows.

When to Use It

  • Narrating documentation without a cloud TTS subscription
  • Cloning a custom voice for consistent audio branding
  • Generating speech offline on a laptop during travel
  • Prototyping voice interfaces without API rate limits
  • Batch-converting written content to audio files

Example Workflow

INPUT

User asks: generate speech from a script using my own voice sample

AGENT
  1. 1

    Export voice embedding from audio sample with pocket-tts export-voice voice.wav voice.safetensors

  2. 2

    Load the TTSModel and retrieve voice state from the safetensors file

  3. 3

    Call model.generate_audio with the voice state and input text

  4. 4

    Save the returned audio array as a 24kHz WAV file using scipy

OUTPUT

A 24kHz mono WAV file with speech in the cloned voice

Requirements

  • HuggingFace account (to access kyutai/tts-voices or kyutai/pocket-tts model weights)

Installation

clawhub install leonaaardob/lb-pocket-tts-skill

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links