openai
OpenAI: GPT Audio
openai/gpt-audio
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to the OpenRouter catalog, openai/gpt-audio is OpenAI's first generally available audio model, accepting text and audio input and returning text and audio output. The catalog describes this snapshot as using an upgraded decoder for more natural-sounding voices and better voice consistency, and lists a 128,000-token context window plus support for tools, structured outputs, and common sampling parameters. These are source-reported capabilities; this pack contains no independent model card or benchmark results, so real-world behavior is unverified here.[1]
Strengths
- Catalog-reported native audio support in both directions: text and audio in, text and audio out.[1]
- The catalog description reports an upgraded decoder aimed at more natural-sounding voices and improved voice consistency.[1]
- 128,000-token context window and support for tool calling and structured outputs, per the catalog.[1]
Limitations
- Evidence is catalog-only: an independent OpenAI model card was not available in this source pack, so claims remain unverified.[1]
- No benchmark results, knowledge cutoff, or measured performance data were included; validate latency, voice quality, and accuracy on your own workload.[1]
- The catalog lists reasoning as null; whether the model supports any explicit reasoning mode is unknown.[1]
Where to use it
Sources
- [1] OpenRouter catalog · OpenAI: GPT AudioSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- openai/gpt-audio
- Creator
- openai
- Added to OpenRouter
- 19.01.2026
- Context length
- 128,000
- Modality
- text+audio->text+audio
- Input modalities
- text, audio
- Output modalities
- text, audio
- Token pricing
- No per-token price in the source snapshot — see OpenRouter for the billing unit
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio · output: audio |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| OpenAI | 128,000 | — | — | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.