Re:Show HN: Make your own voice AI in two clicks
by ton4eg on Tuesday May 13, 2025 @02:41PM
(#43976211)
Way more entertaining than I would expect!
What TTS and ASR models do you use? What sort of latency do you get?
[ Parent
| on HN ]
Re:Show HN: Make your own voice AI in two clicks
by unmute-sh on Tuesday May 13, 2025 @02:54PM
(#43976344)
Thank you! The TTS and ASR are our own unreleased models, but we'll open-source them soon :)
The latency is about 500ms once we detect that it's the bot's turn to speak (roughly 200ms for the LLM's time-to-first token and 300ms for the TTS audio to start), plus a variable time for the semantic pause detection (VAD).
If it's clear that you're done talking, like when you ask a question, the model will reply very fast. If you stop mid-sentence as if you have more to say, it will wait for longer to avoid interrupting you.