Local speech with llamadart: giving Llama Village a voice
Beyond chat with llamadart · Part 3 Pip’s scarf is missing. I wanted Dash to be able to fly over to Mo and ask about it out loud. Dash: “Mo, have you seen Pip’s red scarf?” Mo: “Yes, it's in the reeds beside the pond.” I tried that exchange with local models. For now, it runs in a small command-line program outside Llama Village . The question is a synthetic recording, and Mo gets the scarf’s…
The story describes a process for enabling a character named Mo, a llama, to listen to a recorded question about Pip's red scarf's location and then speak the answer in English. It involves using speech recognition (ASR) to transcribe the audio and then text-to-speech (TTS) to generate the response. The project is set up with a Dart program that loads various models for ASR, dialogue generation, and TTS, with the option to use smaller models for a comparison run.
The program takes a WAV audio file as input, transcribes the speech, and then generates a TTS response based on the transcribed text.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
