OpenAI.fm

Use it when

• You need to compare OpenAI text-to-speech voices and delivery styles in a UI before committing one to your application code
• You want a local playground to iterate on TTS input text and voice settings without writing repeated API scripts

What it solves

Not the fit when

• speech recognition or transcription
• TTS providers other than the OpenAI Speech API
• unattended public deployment (README warns your API key bears all usage costs)
• the optional sharing feature without a hosted Postgres database
• speech-to-text transcription
• offline TTS without an API key
• voice timbre conversion
• production TTS serving

Install

git clone https://github.com/openai/openai-fm.git && cd openai-fm && npm install; create .env in the project root with OPENAI_API_KEY

Invoke

npm run dev, then open http://localhost:3000 and interactively try text-to-speech voices and styles in the UI

Alternatives

No reviewed alternatives recorded yet.