İçeriğe geç
TakoAPI
Becerilere dön

lb-pocket-tts-skill

leonaaardob tarafından

Media & Streaming
729İndirme sayıları clawskills.sh tarafından bildirilir
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

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

Açıklama

Bu Beceri Ne Yapar

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.

Ne Zaman Kullanılır

  • 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

Örnek İş Akışı

GİRİŞ

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

AJAN
  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

ÇIKIŞ

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

Gereksinimler

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

Kurulum

clawhub install leonaaardob/lb-pocket-tts-skill

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar