Models / openai / GPT-4o Audio Preview

GPT-4o Audio Preview

JSON →
openaiaudio

Preview model optimized for audio processing tasks including speech-to-text and audio understanding.

textaudiostreamingfunction-callingtool-use
homepage ↗docs ↗
Specs
Context & limits
128K
context window
16K
max output
Lifecycle
Dates
released2024-12-17
knowledge cutoff2024-06-01
Resources
homepagehttps://platform.openai.com/docs/models/gpt-4o-audio ↗
docshttps://platform.openai.com/docs/api-reference/audio ↗