Text-to-speech (TTS)

Scope

This page is a placeholder generated from the official source file structure.

What to verify

• TODO: Add prerequisites and validation checklist.

Outline (from official headings)

• Supported services
• Edge TTS notes
• Optional keys
• Service links
• Is it enabled by default?
• Config
• Minimal config (enable + provider)
• OpenAI primary with ElevenLabs fallback
• Edge TTS primary (no API key)
• Disable Edge TTS
• Custom limits + prefs path
• Only reply with audio after an inbound voice note
• Disable auto-summary for long replies
• Notes on fields
• Model-driven overrides (default on)
• Per-user preferences
• Output formats (fixed)
• Auto-TTS behavior
• Flow diagram
• Slash command usage

Further reading

• Official source file: tts.md