Skip to main content
Anannas supports sending audio files to compatible models via the API. This guide will show you how to work with audio using Anannas.

​
Audio Input Support

  • OpenAI models support audio inputs (speech-to-text, translation, multimodal).
  • Anthropic models do not support audio inputs. If you pass audio, it will be ignored silently (no error).

​
Audio Inputs

Requests with audio files to compatible models are available via the /chat/completions endpoint with the input_audio content type. Audio files must be base64-encoded and include a format specification. Direct URLs are not supported for audio.

​
Sending Audio Files

{
  "model": "openai/gpt-4o-mini-transcribe",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Please transcribe this audio file." },
        {
          "type": "input_audio",
          "input_audio": {
            "data": "base64_encoded_audio_here",
            "format": "wav"
          }
        }
      ]
    }
  ]
}

​
Supported Formats

  • wav
  • mp3
Was this page helpful?