telegram-voice-to-voice-macos

# Telegram voice-to-voice (macOS Apple Silicon only)

This is an **OpenClaw skill**.

## Requirements

- macOS on Apple Silicon.
- `yap` CLI available in `PATH` (Speech.framework transcription).
  - Project: https://github.com/finnvoor/yap (by finnvoor)
- `ffmpeg` available in `PATH`.

## Compatibility note (important)

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.

## Persistent reply mode (voice vs text)

Store a small per-user preference file in the workspace:

- State file: `voice_state/telegram.json`
- Key: Telegram sender user id (string)
- Values:
  - `"voice"` (default): reply with a Telegram voice note
  - `"text"`: reply with a single text message

If the file does not exist or the sender id is missing: assume `"voice"`.

### Toggle commands

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.

## Getting the inbound audio (.ogg)

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:

1) If the inbound message context includes an attachment path, use it.
2) Otherwise, take the most recent `*.ogg` from `~/.openclaw/media/inbound/`.

## Transcription

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>`
  - If `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]`

## Reply behavior

### Mode...

# telegram-voice-to-voice-macos

An **OpenClaw skill** for a Telegram voice-to-voice workflow on **macOS Apple Silicon only**.

It handles inbound Telegram voice notes (`.ogg`), transcribes locally with `yap` (Speech.framework), generates a reply, and sends the reply back as a Telegram **voice note** using macOS `say` + `ffmpeg`.

## Requirements

- macOS on Apple Silicon
- `yap` in `PATH` (Speech.framework transcription)
  - https://github.com/finnvoor/yap
- `ffmpeg` in `PATH`

## Compatibility

This skill is **macOS-only** (uses `say` and Speech.framework). The registry cannot enforce OS restrictions, so running it on Linux/Windows will fail at runtime.

## Configuration

### Transcription locale

- If `YAP_LOCALE` is set, it will be used (e.g. `it-IT`, `en-US`).
- If `YAP_LOCALE` is not set, the helper script falls back to the **macOS system locale** (from `defaults read -g AppleLocale`).

### TTS voice

- Default is `SYSTEM` (uses the current macOS system voice).
- You can pass a specific voice name to the TTS helper script if needed.

## Files and paths

- Inbound Telegram audio is typically saved by OpenClaw under:
  - `~/.openclaw/media/inbound/`
- Per-user reply mode state:
  - `voice_state/telegram.json`

## Behavior

- Default reply mode: `voice`
- Toggle per user via Telegram text messages:
  - `/audio off` → reply in text
  - `/audio on` → reply with voice note

## Skill instructions

See `SKILL.md` for the full, canonical behavior description used by OpenClaw.