Back to Models

gpt-audio-mini

openaiopenai/gpt-audio-mini

API guide

Chat completion with audio

Send base64-encoded WAV/MP3 audio in the message content. The model replies with text and/or audio β€” identical API pattern to gpt-audio, just at a lower price tier.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio-mini",
    "modalities": ["text", "audio"],
    "audio": { "voice": "alloy", "format": "wav" },
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "What does this audio say?" },
          { "type": "input_audio", "input_audio": { "data": "<BASE64_AUDIO>", "format": "wav" } }
        ]
      }
    ]
  }'

Streaming audio chat

Stream text transcript tokens in real-time while receiving the full audio in the final message.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio-mini",
    "modalities": ["text", "audio"],
    "audio": { "voice": "nova", "format": "wav" },
    "stream": true,
    "messages": [
      { "role": "user", "content": "Tell me a story in 30 seconds." }
    ]
  }'

Tool/function calling

gpt-audio-mini supports tool calling with audio context β€” usable in the same way as text-only models.

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio-mini",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "input_audio", "input_audio": { "data": "<BASE64_AUDIO>", "format": "wav" } },
          { "type": "text", "text": "Extract the booking reference and the date mentioned in this audio." }
        ]
      }
    ],
    "tools": [
      {
        "type": "function",
        "function": {
          "name": "extract_booking",
          "description": "Extract booking reference and date",
          "parameters": {
            "type": "object",
            "properties": {
              "reference": { "type": "string" },
              "date": { "type": "string" }
            },
            "required": ["reference", "date"]
          }
        }
      }
    ],
    "tool_choice": "auto"
  }'
Fact ledger β€” every claim on this page traces here
sourceURLretrieved
Release dateDesign for Online / OpenRouter β†—2026-05-29verified
Context windowOpenRouter β†—2026-05-29verified
Max output tokensOpenRouter β†—2026-05-29verified
Supported modalitiesdevelopers.openai.com β†—2026-05-29verified
Supported capabilitiesplatform.openai.com β†—2026-05-29verified
Licenseβ€”β€”verified
Audio quality (upgraded decoder)Design for Online β†—2026-05-29to verify
OpenAI launches gpt-audio and gpt-audio-miniDesign for Online / OpenRouter β†—2026-05-29verified
Help & contact