GPT Audio Mini
Built by OpenAI, GPT Audio Mini is an speech-and-audio model with a 128K token context window. 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...
by OpenAI · 128K token context window
Best for
- speech-to-text transcription
- meeting and audio transcription
Ways to use GPT Audio Mini in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your OpenAI API key. osFoundry discovers GPT Audio Mini automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
GPT Audio Mini vs similar models
| Model | Org | Params | Context | Input price | Self-host |
|---|
| GPT Audio Mini | OpenAI | — | 128K | $ 0.600 /1M | API only |
| Voxtral Small 24B 2507 | Mistral | — | 32K | $ 0.100 /1M | API only |
| GPT Audio | OpenAI | — | 128K | $ 2.50 /1M | API only |
| GPT-4o Audio | OpenAI | — | 128K | $ 2.50 /1M | API only |
Licence
Hosted — usage subject to provider terms — Hosted-only model — usage governed by the provider's API terms. Bring your own provider key.
No weights distributed; usage subject to provider terms.
Frequently asked about GPT Audio Mini
How much does GPT Audio Mini cost?
GPT Audio Mini is metered at $ 0.600 /1M for input, and $ 2.40 /1M for output. Bring your own OpenAI API key — osFoundry passes through provider pricing without markup.
Can I use GPT Audio Mini commercially?
Commercial use is allowed with conditions. Hosted-only model — usage governed by the provider's API terms. Bring your own provider key. No weights distributed; usage subject to provider terms.
What is the context window of GPT Audio Mini?
GPT Audio Mini supports a 128K token context window.
Can I run GPT Audio Mini locally?
No — GPT Audio Mini is hosted only and accessed via the OpenAI API.
What is GPT Audio Mini best at?
GPT Audio Mini is well-suited to speech-to-text transcription, meeting and audio transcription.
How do I use GPT Audio Mini in osFoundry?
Paste your OpenAI API key in the key dialog (or deploy the open weights for self-hostable models), assign GPT Audio Mini to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by OpenAI on January 19, 2026. Source: https://openrouter.ai/openai/gpt-audio-mini