Enterprise DNAEnterprise DNA
LModelsAudio
OpenAI logo

GPT Audio

by OpenAI

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 con

Visit OpenAISubmit your build →
GA

Models

GPT Audio

Added 10 July 2026

#openai

Overview

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...

Best for

Best for
Audio input and spoken responses

How to use / API access

Call via OpenRouter with model id `openai/gpt-audio`.

  • openrouter · openai/gpt-audio Docs

OpenRouter id: openai/gpt-audio

Notes

GPT Audio is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Prototyping a spoken assistant with explicit turn boundaries
  • text, audio input; text, audio output on the listed OpenRouter route

Cons

  • Assuming batch audio implies realtime transport support
  • Estimating audio requests with only text-token prices
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →

USAGE / OPENROUTER

How much GPT Audio is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
179M ▲47.4%
Requests, last 7 days
230K
Tool calls, last 7 days
1K
Price per million tokens
$2.5 in · $10 out
050M100M19 Sept: 6.6M tokens, 6K requests20 Sept: 10.3M tokens, 7.9K requests21 Sept: 7.9M tokens, 20.8K requests22 Sept: 9M tokens, 13.2K requests23 Sept: 11.9M tokens, 19.6K requests24 Sept: 19.7M tokens, 34.5K requests25 Sept: 20.6M tokens, 30.7K requests26 Sept: 13M tokens, 30.5K requests27 Sept: 11.3M tokens, 26.7K requests28 Sept: 17.6M tokens, 41.3K requests29 Sept: 15.7M tokens, 26.3K requests30 Sept: 14.9M tokens, 29.7K requests1 Oct: 11.1M tokens, 18.5K requests2 Oct: 12.7M tokens, 24.3K requests3 Oct: 47.4M tokens, 129K requests4 Oct: 10M tokens, 20.5K requests5 Oct: 20.8M tokens, 22.2K requests6 Oct: 13.6M tokens, 16.1K requests7 Oct: 18.2M tokens, 19K requests8 Oct: 15.4M tokens, 21.5K requests9 Oct: 19.5M tokens, 19K requests10 Oct: 15.7M tokens, 19K requests11 Oct: 18.1M tokens, 19.6K requests12 Oct: 28.2M tokens, 21.4K requests13 Oct: 21M tokens, 26.3K requests14 Oct: 17.1M tokens, 26.4K requests15 Oct: 32.8M tokens, 34.6K requests16 Oct: 52.5M tokens, 79K requests17 Oct: 13.6M tokens, 16.5K requests18 Oct: 13.3M tokens, 26.2K requests19 Sept3 Oct17 Oct18 OctSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GPT Audio.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-10-20. Hosting routes and app features can differ.

DeveloperOpenAI
Exact model identifieropenai/gpt-audio
Inputtext, audio
Outputtext, audio
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Prototyping a spoken assistant with explicit turn boundaries
  • Testing text and audio response consistency

Watch for

  • Assuming batch audio implies realtime transport support
  • Estimating audio requests with only text-token prices

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Read aloud: Your order contains three items and arrives on Tuesday. Use a calm neutral voice and add no other information.

Check the result: Listen for the exact item count and delivery day; compare any text response to the speech.

Compare another approach

Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

openai/gpt-audio: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-10-20
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Run a reliable agentWorkflow & starter prompt ↗

Check the source

Price date: 2026-10-20. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Compare this model with alternatives →