Audio Input
Use the input_audio content-part to send audio to audio-capable models.
Example
Section titled “Example”curl https://llmtr.com/v1/chat/completions \ -H "Authorization: Bearer sk_your_key" \ -H "Content-Type: application/json" \ -d '{ "model": "google/gemini-2.5-flash", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Transcribe and briefly summarize." }, { "type": "input_audio", "input_audio": { "data": "BASE64_WAV_DATA", "format": "wav" } } ] } ] }'Supported formats
Section titled “Supported formats”wavmp3flacoggwebm
Size limit
Section titled “Size limit”- Inline base64: < 1 MB recommended.
- Longer audio: upload via Files API and reference
file_id.
File ID reference
Section titled “File ID reference”{ "type": "input_file", "input_file": { "file_id": "file_xxx", "mime_type": "audio/wav" }}Supported models
Section titled “Supported models”Audio input is mainly available on Google Gemini family. Check:
curl "https://llmtr.com/api/models?modality=audio" \ -H "Authorization: Bearer sk_your_key"