GPT Audioon Krater.ai
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced
Released January 19, 2026
Specifications
GPT Audio at a glance
Context
128K tokens
Max output
16.4K tokens
Input
Text, Audio
Output
Text, Audio
Input price
$2.50 / 1M
Output price
$10.00 / 1M
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Compare
Compare GPT Audio
GPT Audio vs GPT Audio Mini
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.
Open comparisonGPT Audio vs GPT-5.5 Pro (batch)
GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.
Open comparisonGPT Audio vs GPT-4o (batch)
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.
Open comparisonFAQ
Questions about GPT Audio
Clear answers based on the model catalog and Krater access.
Use GPT Audio in your API
Connect with Krater's unified API.