本文へスキップ
TakoAPI
スキル一覧に戻る

macos-local-voice

strrl 作

Image & Video Generation
1.1kダウンロード数はclawskills.shが公開している値です
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

Local STT and TTS on macOS using native Apple capabilities.

説明

このスキルでできること

Local speech-to-text and text-to-speech on macOS using Apple's native Speech.framework and say command. All processing runs on-device with no network calls or API keys. Supports multiple languages, voice quality tiers, and audio output in ogg/opus or aiff formats.

Unlike cloud STT/TTS APIs, this runs fully offline with no usage costs, no data leaving the device, and no account or key setup required.

使いどころ

  • Transcribing recorded voice memos without uploading to a cloud service
  • Having long documents read aloud while multitasking
  • Sending voice notes in chat apps from generated audio files
  • Dictating in Chinese, Japanese, or other languages with locale-specific recognition
  • Building offline voice interfaces that work without internet

ワークフロー例

入力

User asks: Read this paragraph aloud in French

エージェント
  1. 1

    Run voices.mjs best fr_FR to find the highest quality available French voice

  2. 2

    Run voices.mjs check to confirm the voice is downloaded and ready

  3. 3

    Run tts.mjs with the text and selected voice to generate an audio file

  4. 4

    Send the generated file path as a voice note using the message tool

出力

Audio file generated at ~/.openclaw/media/outbound/tts_<timestamp>.ogg and sent as a voice note

要件

  • yap CLI installed via Homebrew: brew install finnvoor/tools/yap
  • ffmpeg installed via Homebrew for ogg/opus output (optional): brew install ffmpeg

インストール

clawhub install strrl/macos-local-voice

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク