GPT Audio Mini
GPT Audio Mini is a cost-efficient model released by OpenAI that supports both text and audio inputs and outputs. It features an upgraded decoder designed to produce more natural-sounding voices with improved consistency.
GPT Audio Mini specs and pricing
- Provider: OpenAI
- Released: January 19, 2026
- Context window: 128K tokens
- Max output: 16K tokens
- Input: text, audio
- Output: text, audio
- Price: $0.60 input / $2.40 output per 1M tokens
- Tool calling: yes
What GPT Audio Mini is good at
- Developing voice-based conversational applications
- Generating natural-sounding audio responses from text
- Processing audio files for transcription or analysis
To-dos to try with GPT Audio Mini
- Upload a long audio recording and ask the model to summarize the key discussion points.
- Provide a written script and have the model generate an audio file with a natural-sounding voice.
- Use the tool-calling capability to trigger external actions based on spoken user commands.
FAQ
- What is the primary focus of GPT Audio Mini? It is a cost-efficient model designed to provide high-quality, natural-sounding voice output and support for audio-based interactions.
- Can this model process both text and audio? Yes, the model is capable of handling both text and audio as input and can generate both text and audio as output.
- How much does GPT Audio Mini cost? GPT Audio Mini costs $0.60 per million input tokens and $2.40 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 2.02 credits ($1 = 100 credits).
- What is the context window of GPT Audio Mini? GPT Audio Mini can read up to 128K tokens at once and write up to 16K tokens in one reply.
- Can I use GPT Audio Mini without coding? Yes. In todo.is you pick GPT Audio Mini as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.