IdeaSift

Home Assistant voice users hear Markdown and model tags aloud

Home Assistant users sending LLM responses or alerts to text-to-speech can hear Markdown punctuation, such as asterisks, and sometimes model “thinking” tags spoken literally. Some speech engines normalize formatting, but users report that Piper and other setups do not; workarounds include changing prompts or patching Piper rather than adding a simple cleanup step before speech.

For home Assistant voice-assistant users. Mentioned from Feb 2025 to May 2025 on product forums.

5 different people described this problem in 3 separate discussions.

Week of 2026-07-13: 0Week of 2026-07-20: 0Week of 2026-07-27: 0Week of 2026-08-03: 0Week of 2026-08-10: 0Week of 2026-08-17: 0Week of 2026-08-24: 0Week of 2026-08-31: 0Week of 2026-09-07: 0Week of 2026-09-14: 0Week of 2026-09-21: 0Week of 2026-09-28: 0
0 mentions in the last 12 weeks
Indie fit
3.0/10
Pain
5.7/10
Frequency
6.5/10
Willingness to pay
0.0/10
Momentum
5.0/10
Who pays
Consumers
Competition
Low
Build difficulty
Medium

What people said

Quoted word for word. Follow a link to read the whole discussion.

  1. These characters are then said by the TTS (some tts engines do the normalisation themselves, but most can’t, Piper included). It would be a great idea to add a simple filter (as an option) to the assist pipeline (after the conversation module) that removes the formatting from the text
    mchk on community.home-assistant.ioFeb 2025+10 likesAsked for a tool
  2. Got tired of waiting and added the changes to the piper myself Edit handler.py
    mchk on community.home-assistant.ioMay 2025Has a workaround
Build brief

See what to build and who will buy it

  • 1 product idea with the smallest useful version and pricing
  • 3 places to find your first customers
  • 4 more quotes from people who have this problem
  • Current workarounds, existing solutions and risks