Single File Mode

Audio version — Estimated duration: 2 min 11 sec

Convert one markdown file to audio with a single command.

python tts_single.py doc.md

Examples

# Everything online (default)
python tts_single.py doc.md
 
# Fully local
python tts_single.py doc.md --local
 
# Mixed: local LLM, online TTS
python tts_single.py doc.md --llm local --tts online
 
# Custom voice
python tts_single.py doc.md --voice en-GB-SoniaNeural

Output

• doc.mp3 (or doc.wav for Piper) — in the same directory as the source
• The source doc.md gets an <audio> tag injected at the top
• Voice-friendly markdown saved to voice-notes/doc.md

Arguments

See CLI Reference for all flags. The single-file mode accepts the same backend flags as pipeline mode.