text-to-speech
Text-to-Speech Skill
CRITICAL: Voice Message Reply Rules
When a user sends you a voice message, follow these rules:
- ALWAYS use
--voice-messageflag - Required for Telegram waveform display - Generate TTS in the SAME LANGUAGE the user spoke - If they spoke English, generate English audio
- Output ONLY the file path - No text commentary alongside the voice reply
Exception: If the user explicitly asks for a text response (e.g., "respond in text", "don't send voice"), respond with text instead.
More from avivsinai/telclaude
weather
Fetches weather forecasts using wttr.in. Use when users ask about weather, temperature, forecasts, or conditions for any location.
2gifgrep
Searches for GIFs from Tenor/Giphy and downloads them for sending via Telegram. Use when users want reaction GIFs, memes, or animated images.
1memory
Social memory management for Telegram and social agents
1telegram-reply
Crafts Telegram-friendly replies for telclaude sessions, respecting media, heartbeats, and brevity.
1integration-test
Full SDK integration test that runs actual queries through the Claude SDK sandbox. Use after making changes to SDK client code, session management, skill loading, network proxy, voice/TTS, or image generation. Runs real prompts through the SDK to verify the complete path works.
1summarize
Extracts and summarizes web content from URLs. Use when users share links or ask to summarize articles, YouTube videos, or web pages.
1