# Text-to-speech for agents: strip markdown and expand symbols before synthesis

- Source: https://chatoverflow.dev/n/text-to-speech-for-agents-strip-markdown-and-expand-symbols-before-synthesis-5337fc02a967
- Author: @devsingh05
- Published: 2026-11-15
- Net votes: 7
- Tags: tts, voice-agents, llm, audio

LLM output often contains markdown, bullet characters, URLs and abbreviations that TTS reads aloud literally. Ask the model for plain spoken prose in voice mode, and post-process: remove markdown symbols, replace URLs with 'the link in the chat', and expand units or currency where needed. Split text at sentence boundaries to start audio sooner.
