メニュー
Telegram voice-to-voice for macOS Apple Silicon: transcribe inbound .ogg voice notes with yap (Speech.framework) and reply with Telegram voice notes via say+ffmpeg. Not compatible with Linux/Windows.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/johnalbertini14-glitch/openclaw-skills --skill telegram-voice-to-voice-macosコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Use this skill to create a Polymarket wallet for your agent and trade on prediction markets. Browse markets, place bets, manage positions — all without exposing private keys.
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.
SOC 職業分類に基づく
| name | telegram-voice-to-voice-macos |
| description | Telegram voice-to-voice for macOS Apple Silicon: transcribe inbound .ogg voice notes with yap (Speech.framework) and reply with Telegram voice notes via say+ffmpeg. Not compatible with Linux/Windows. |
| metadata | {"openclaw":{"os":["darwin"],"requires":{"bins":["yap","ffmpeg","say","defaults"]}}} |
This is an OpenClaw skill.
yap CLI available in PATH (Speech.framework transcription).
ffmpeg available in PATH.This skill is macOS-only (uses say + Speech.framework). The skill registry cannot enforce OS restrictions, so installing/running it on Linux/Windows will result in runtime failures.
Store a small per-user preference file in the workspace:
voice_state/telegram.json"voice" (default): reply with a Telegram voice note"text": reply with a single text messageIf the file does not exist or the sender id is missing: assume "voice".
If an inbound text message is exactly:
/audio off → set state to "text" and confirm with a short text reply./audio on → set state to "voice" and confirm with a short text reply.Telegram voice notes often show up as <media:audio> in message text.
OpenClaw saves the attachment to disk (typically .ogg) under:
~/.openclaw/media/inbound/Recommended approach:
*.ogg from ~/.openclaw/media/inbound/.Default locale: macOS system locale.
Optional env:
YAP_LOCALE — override the transcription locale (e.g. it-IT, en-US).Preferred:
yap transcribe --locale "${YAP_LOCALE:-<system>}" <path.ogg>
YAP_LOCALE is not set, the helper script will use the macOS system locale (from defaults read -g AppleLocale).If transcription fails or is empty: ask the user to repeat or send text.
Helper script:
scripts/transcribe_telegram_ogg.sh [path.ogg]Voice default: SYSTEM (uses the current macOS system voice). You can override by passing a specific voice name to the helper script.
scripts/tts_telegram_voice.sh "<reply text>" [SYSTEM|VoiceName]The script prints the generated .ogg path to stdout.
.ogg back to Telegram as a voice note (not a generic audio file):message tool with asVoice: true and media: <path.ogg>replyTo to thread the responseNotes:
SYSTEM to rely on the current macOS system voice (recommended).Reply with a single text message:
Transcription: <...>Reply: <...>