ArchestackGitHub ↗ (opens in a new tab)

#1515th of 16 in Voice and realtime

openai-fm

Next.js demo app for trying OpenAI text-to-speech models

Live demo ↗ (opens in a new tab)Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
2.9k
License
MIT
Last commit
Dec 2025
Language
TypeScript

Overview

OpenAI.fm is the source for the openai.fm demo, a web interface for generating speech through the OpenAI Speech API. It is a Next.js app that needs an OpenAI API key; an optional Postgres database enables a sharing feature. It is a demo reference rather than a general-purpose starter.

Who it is for: Developers learning to build on the OpenAI Speech API

Strengths

  • Official OpenAI reference for calling the Speech API from Next.js
  • Runs with only an API key; no database needed for core use
  • MIT license
  • Live hosted demo at openai.fm

Weaknesses

  • Tied to the OpenAI API; no other TTS providers
  • No Dockerfile or compose file in the README
  • Sharing feature requires a hosted Postgres database
  • Maintainers say they may not review all issues or PRs

What it needs

  • TypeScript, OpenAI text-to-speech models
  • Needs OpenAI API, Postgres (optional, sharing only)
  • env example file

Also in Voice and realtime

See all 16
Also in Voice and realtime
RankProjectScore
1agent-starter-reactNext.js voice assistant frontend for LiveKit Agents947 stars, MIT51 out of 100
2agent-starter-pythonPython voice agent on LiveKit Agents with turn detection and simulations264 stars, MIT50 out of 100
3agent-starter-nodeNode.js voice agent on LiveKit Agents with turn detection and simulations114 stars, MIT50 out of 100
#4voice-ui-kitReact components and templates for Pipecat voice agent frontends419 stars, BSD-2-Clause45 out of 100
#5pipecat-examplesRunnable Pipecat voice agent examples for phone, web and deployment395 stars, BSD-2-Clause41 out of 100