claude-code icon indicating copy to clipboard operation
claude-code copied to clipboard

[Feature request] Text-to-speech output

Open rbinnun opened this issue 8 months ago • 1 comments

Description: It would be helpful to have a text-to-speech option that reads Claude's responses aloud. This would improve accessibility and allow users to listen to responses while multitasking.

Proposed implementation:

  • Add a --tts flag or setting to enable text-to-speech
  • Integrate with system TTS (espeak on Linux, say on macOS, etc.)
  • Option to automatically read responses or trigger on demand

Use case: Currently there's no easy way to have Claude's responses read aloud without manually copying text to external TTS tools, which interrupts the workflow.

Alternative considered: Piping output to external TTS tools, but Claude Code's interactive nature makes this difficult.

rbinnun avatar Jun 17 '25 11:06 rbinnun

Hey @rbinnun! 👋

Your TTS feature request is exactly what Voice Mode provides today - and much more!

Voice Mode delivers:

  • Full TTS for Claude's responses - Every response can be spoken aloud
  • Beyond system TTS - High-quality voices from OpenAI or local Kokoro
  • Two-way conversations - Not just TTS output, but full voice interactions

Simple setup:

# Add to Claude Code
claude mcp add voice-mode --env OPENAI_API_KEY=your-key -- uvx voice-mode

# Start using TTS
claude converse

Accessibility features you mentioned:

✅ Automatic reading of responses
✅ On-demand triggering
✅ Works while multitasking
✅ No manual copying needed

Bonus capabilities:

  • Emotional speech - Claude can speak with different tones
  • Multiple voices - Choose from various voice options
  • Local option - Use Kokoro TTS for fully offline operation
  • Cross-platform - Works on Linux, macOS, and Windows (WSL)

Instead of piping to external tools, Voice Mode integrates directly with Claude Code through MCP, making it seamless and interactive.

Would this solve your accessibility and multitasking needs? Happy to help you get started!

getvoicemode avatar Jun 30 '25 21:06 getvoicemode

Briny Your Own Keys solution: https://github.com/robdmac/talkito

Just pip install, talkito claude then say "start TTS" (the ASR, Slack, WhatsApp etc is all optional)

robdmac avatar Jul 01 '25 09:07 robdmac

This issue has been inactive for 30 days. If the issue is still occurring, please comment to let us know. Otherwise, this issue will be automatically closed in 30 days for housekeeping purposes.

github-actions[bot] avatar Oct 10 '25 10:10 github-actions[bot]