Chat then Speak
A 2-step recipe with OpenAI. We can help you get access.
Recipe · 2 steps
Chat then Speak
with OpenAI
Create a chat reply and convert it to speech audio.
- Create a chat completion answering the user prompt.
- Synthesize the chat reply into spoken audio.
What you'll need to have ready
- apiKey: OpenAI API key used as a Bearer token.
- chatModel: The chat model id (e.g. gpt-4o-mini).
- prompt: The user prompt to answer.
- speechModel: The text-to-speech model id (e.g. gpt-4o-mini-tts or tts-1).
- voice: The voice to use for synthesis (e.g. alloy).
For your developer
Arazzo workflow openai:chat-then-speak, 2 operations: createChatCompletion → createSpeech. Specs on APIs.io.