Skip to content

feat: send voice messages via Telegram sendVoice API#34

Open
dmitryanchikov wants to merge 1 commit intomoazbuilds:masterfrom
dmitryanchikov:feat/voice-sending
Open

feat: send voice messages via Telegram sendVoice API#34
dmitryanchikov wants to merge 1 commit intomoazbuilds:masterfrom
dmitryanchikov:feat/voice-sending

Conversation

@dmitryanchikov
Copy link
Copy Markdown
Contributor

Summary

  • Parse [voice:/path/to/file.ogg] directives from Claude responses
  • Deliver voice files as native Telegram voice messages via sendVoice API
  • Voice messages sent before any remaining text; if only voice — no empty text sent

Test plan

  • TTS generates [voice:...] directive, parsed correctly
  • Voice file delivered as Telegram voice message (not plain text)
  • Text after voice directive still sent as regular message
  • Missing/invalid voice paths silently skipped

🤖 Generated with Claude Code

Parse [voice:/path/to/file.ogg] directives from Claude responses
and deliver them as native Telegram voice messages instead of
plain text. Voice files are sent before any remaining text.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fenrur added a commit to Fenrur/claudeclaw that referenced this pull request Mar 13, 2026
…zbuilds#35)

- Delegate voice transcription to Claude via file path (no local whisper)
- Parse rate limit reset time from Claude output
- Global rate limit state to pause heartbeats/jobs
- Voice directive [voice:/path] for TTS responses
- Text document download and inline reading
- Rate limit pre-check in Telegram handler

Supersedes PRs moazbuilds#32, moazbuilds#33, moazbuilds#34.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant