Skip to content
#

ai-speech

Here are 18 public repositories matching this topic...

Production-ready voice agents and speech pipelines: STT → LLM/Agent → TTS, voice receptionists, telephony, call recording, tool/function calling. Built with Twilio, OpenAI Whisper, ElevenLabs, Vapi/Retell, FastAPI, WebSockets, ffmpeg; designed for deployment, monitoring, and real-world reliability

  • Updated Feb 22, 2026
  • TypeScript

ai-text-to-speech is a powerful straightforward Node.js module for generating speech audio from text using the OpenAI API (support for other TTS providers in the works). It offers a simple and robust interface to convert text into high-quality speech audio files in various formats and voices. ☕️ Buy me a coffee: https://buymeacoffee.com/jkapron

  • Updated Jul 9, 2026
  • JavaScript

This dataset contains AI-generated podcast episodes produced using Google's NotebookLM "Audio Overview" feature, along with speaker diarization annotations generated using WhisperX. Each episode is a synthetic two-host conversation generated by NotebookLM from source documents, transcribed and diarized to identify who is speaking when.

  • Updated Jul 7, 2026

Improve this page

Add a description, image, and links to the ai-speech topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the ai-speech topic, visit your repo's landing page and select "manage topics."

Learn more