{
  "id": 14355573,
  "title": "Local speech with llamadart: giving Llama Village a voice",
  "url": "https://urgent.news/2026/10/14/local-speech-with-llamadart-giving-llama-village-a-voice",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-14T03:03:34.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/gde/local-speech-with-llamadart-giving-llama-village-a-voice-5b7m"
  },
  "original_language": "en",
  "account": "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.",
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}