Converse in audio
Generate spoken responses to incoming speech and conversational context.
Desired outcome
Spoken responses that continue an interactive conversation.
Explore from the outcome
Where this function can lead
These documented connections are starting points for selection, not a ranked list.
Model releases
Identifiable models documented for this function.
- GPT-Audio-1.5
Accept text or audio and produce spoken or text responses through Chat Completions.
Link evidence: GPT-Audio-1.5 model page
- GPT-Live 1
Hold full-duplex spoken conversations with simultaneous listening and speech output.
Link evidence: GPT-Live 1 model page
Typical inputs
- Incoming speech
- Conversation history and optional text or visual context
Typical outputs
- Generated speech response
- Streamed audio where supported
Sources
Last reviewed 2026-10-04