# openai/openai-fm

Code for openai.fm, a demo for the OpenAI Speech API

Repository: https://github.com/openai/openai-fm
Canonical: https://ross.abutalabs.com/products/openai-fm
Homepage: https://openai.fm
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-03-03T16:27:33+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 36
- inputs: {"age_days": 505, "days_push": 183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2887, forks 7941 (observed 2026-08-28T04:07:28.198615+00:00)

## What it is
OpenAI.fm is an interactive web demo showcasing OpenAI's text-to-speech models, built with Next.js and the OpenAI Speech API. It lets users enter text, choose voices and controls, and generate spoken audio, with optional sharing via a Postgres-backed feature.

## Use cases
- try out openai text-to-speech voices in a browser
- generate speech audio from text with different voice styles
- self-host a tts demo using the openai speech api
- explore voice controls like tone and emotion for tts
- demo app to learn the openai audio createSpeech endpoint

## When to choose
- you want a ready-made interactive UI to experiment with OpenAI TTS models
- you need a reference Next.js implementation of the OpenAI Speech API
- you want to self-host a text-to-speech playground with your own API key

## When to avoid
- you need production text-to-speech without depending on the OpenAI API
- you want offline or open-source TTS models
- you need a backend library or SDK rather than a demo web app

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, web-framework, chat-interface
- domain: speech-processing, artificial-intelligence, web-development, large-language-models
- platform: self-hosted
- tags: text-to-speech, openai-api, nextjs, demo-app, voice-generation, typescript, nodejs, web-server, docker

## Member repositories
- openai/openai-fm (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:28.198615+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:35:22.389148+00:00, confidence not recorded.
  - readme: https://github.com/openai/openai-fm (fetched 2026-08-28T04:07:28.198615+00:00, sha 64c57916dc97)
- Data as of 2026-08-30T08:39:29.467469+00:00.