Lewati ke konten
TakoAPI
Kembali ke skill

lb-pocket-tts-skill

oleh leonaaardob

Media & Streaming
729Unduhan dilaporkan oleh clawskills.sh
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

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

Deskripsi

Apa yang Dilakukan Skill Ini

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.

Kapan Menggunakannya

  • 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

Contoh Alur Kerja

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

Persyaratan

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

Instalasi

clawhub install leonaaardob/lb-pocket-tts-skill

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan