GPT-Audio
Audio model for speech input and output with the Chat Completions API
- Price per 1M tokens
- $2.5 / $10 input / output · OpenAI
- Context window
- 128K tokens in · 16.4K out
The GPT-Audio-1.5 line
2 releases in the GPT-Audio-1.5 line.
A newer release is out: GPT-Audio-1.5.
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
OpenAI's past year
23 release days in the past year, about one every 16 days. The next is expected around Nov 5, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOctNov
Specifications
RELEASE DATEAug 28, 2025
WEIGHTSClosed weights
CONTEXT WINDOW128K
MAX OUTPUT16.4K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, audio/wav, audio/mpeg
OUTPUTStext, audio/wav, audio/aac, audio/mpeg, audio/flac, audio/opus, audio/pcm
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.