Pular para o conteúdo
TakoAPI
Voltar às skills

her-voice

por matusvojtek

Speech & Transcription
474Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Give your agent a voice.

Descrição

O que esta skill faz

Her Voice adds spoken audio responses to an agent using Kokoro TTS, a local 82M-parameter neural model. Audio streams on-device with no API keys or cloud dependencies. Supports a real-time LED visualizer, a background daemon for low latency, and voice blending between multiple voices.

Runs entirely on-device with no API keys or cloud costs, while still achieving sub-second first-audio latency via streaming and an optional warm-model daemon.

Quando usá-la

  • Hearing agent replies read aloud while working hands-free
  • Listening to long code summaries without reading the screen
  • Using persist mode as a standalone voice station for pasted text
  • Saving spoken responses as WAV files for later playback
  • Getting instant audio feedback when the agent starts responding

Exemplo de fluxo de trabalho

ENTRADA

User asks: Read this summary aloud

AGENTE
  1. 1

    Check if voice mode is enabled or requested by the user

  2. 2

    Play a macOS notification sound immediately for instant feedback while TTS generates

  3. 3

    Call speak.py with the response text

  4. 4

    Stream audio output while the visualizer animates in real-time

  5. 5

    Display the text response alongside the audio for accessibility

SAÍDA

Spoken audio plays through speakers with a floating LED visualizer overlay; text response also shown in the terminal

Requisitos

  • espeak-ng installed (brew install espeak-ng on macOS, apt install espeak-ng on Linux)

Instalação

clawhub install matusvojtek/her-voice

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links