Audio - Baseten

Model APIs support audio input on audio-capable models. These models accept audio alongside text in the same request, using the audio_url content type, and process both modalities together: they can transcribe speech, answer questions about audio content, or reason over a recording and a text prompt at once. Not all models support audio. Check the table below before sending audio inputs.

Supported models

Model	Slug
Inkling	`thinkingmachines/inkling`

Send an audio request

Use the audio_url content type to include audio in your messages. The request shape matches vision requests with audio_url in place of image_url. Baseten retrieves audio URLs from the inference service, so the URL must be reachable over HTTPS from Baseten’s environment (for example your own object storage or other hosts that allow server-side fetches). Prefer stable, direct HTTPS links. Base64 data: URLs also work, but the request body is capped at 5 MB, so pass audio by URL when you can. Send audio as WAV sampled at 16kHz. Recordings under 20 minutes give the best results. Send a recording alongside a text prompt like this:

Python
JavaScript
cURL

audio.py

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://inference.baseten.co/v1",
    api_key=os.environ["BASETEN_API_KEY"],
)

response = client.chat.completions.create(
    model="thinkingmachines/inkling",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Summarize what is said in this recording.",
                },
                {
                    "type": "audio_url",
                    "audio_url": {
                        "url": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav",
                    },
                },
            ],
        }
    ],
)

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

audio.js

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://inference.baseten.co/v1",
    apiKey: process.env.BASETEN_API_KEY,
});

const response = await client.chat.completions.create({
    model: "thinkingmachines/inkling",
    messages: [
        {
            role: "user",
            content: [
                {
                    type: "text",
                    text: "Summarize what is said in this recording.",
                },
                {
                    type: "audio_url",
                    audio_url: {
                        url: "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav",
                    },
                },
            ],
        },
    ],
});

console.log(response.choices[0].message.content);

Request

curl https://inference.baseten.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{
    "model": "thinkingmachines/inkling",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Summarize what is said in this recording."
          },
          {
            "type": "audio_url",
            "audio_url": {
              "url": "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav"
            }
          }
        ]
      }
    ]
  }'

Pricing

There is no additional per-request fee for audio. Audio is converted to input tokens and priced at the model’s standard input rate. Longer recordings produce more tokens and cost more to process. See the Model APIs pricing page for per-model rates.

Next steps

Vision

Send images and videos alongside text

Chat Completions reference

Full request and response schema for the audio_url content type

​Supported models

​Send an audio request

​Pricing

​Next steps