Bitdeer AI Docs
Switch language
GuidesAPI ReferenceGPU Cloud
LLM

Audio Input

Send audio via input_audio for transcription, summarization, and analysis.

Pass audio in the messages array with the input_audio content type on nvidia/Nemotron-3-Nano-Omni-30B-A3B, alongside optional text instructions.

Supported model

Model IDProvider
nvidia/Nemotron-3-Nano-Omni-30B-A3BNVIDIA

For image input, see the Vision guide. The full model list is in the Model Catalog.

Audio via URL

from openai import OpenAI

client = OpenAI(
    base_url="https://api-inference.bitdeer.ai/v1",
    api_key="YOUR_API_KEY",
)

response = client.chat.completions.create(
    model="nvidia/Nemotron-3-Nano-Omni-30B-A3B",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://example.com/meeting.wav",
                        "format": "wav",
                    },
                },
                {
                    "type": "text",
                    "text": "Transcribe this audio and summarize the key points.",
                },
            ],
        }
    ],
    max_tokens=1024,
)

print(response.choices[0].message.content)

Notes

  • input_audio.data accepts a public URL or Base64-encoded audio bytes.
  • Set input_audio.format to the container/codec your file uses (for example wav, mp3).
  • Streaming is supported with audio inputs when stream=true.

Last updated on

Vision Language Models

Send images to vision-language models for understanding, description, and analysis.

Function Calling

Let models invoke external tools and APIs through function definitions.

On this page

Audio Input · Bitdeer AI