Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
2 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Streaming speech-to-text model for low-latency transcript deltas from live audio
1 provider
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...
A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| GPT-Realtime-2.1openai/gpt-realtime-2.1 | OpenAI |
128K | $4 | $24 | 2026-07-06 | ||
| GPT Realtime Whisperopenai/gpt-realtime-whisper | OpenAI |
Not documented | — | — | 2026-05-07 | ||
| OpenAI: GPT Audioopenai/gpt-audio | OpenAI |
128K | $2.5 | $10 | — | ||
| OpenAI: GPT Audio Miniopenai/gpt-audio-mini | OpenAI |
128K | $0.6 | $2.4 | — |