Name: Nova-2 Automotive API
Brand: Deepgram

Overview

What is Nova-2 Automotive API?

Nova-2: Advanced, versatile ASR model for diverse transcription needs.

Technical Specifications
- Supported inputs: Audio
- Output: Text

Performance Benchmarks
[embed]

Nova-2 Automotive API Pricing
- Pricing on request

Where to Use Nova-2 Automotive

Transcription
Convert calls, meetings, and media into accurate, searchable text.

Captioning and indexing
Generate subtitles and make audio archives searchable.

Use cases

The available source material for this exact model only clearly documents that Nova-2 Automotive is optimized for automotive-oriented vocabulary and is suited to in-car applications. It is also listed alongside use cases such as call analytics and transcription pipelines, but those are not stated as specific to the automotive variant in the source material.

In-car applications: The model is documented as “best for” in-car applications, which aligns with its automotive specialization.

Automotive vocabulary transcription: It is described as optimized for audio with automotive-oriented vocabulary, indicating suitability for speech recognition in vehicle-related settings.

English automotive speech recognition: The model is listed as an English model option, so its documented use is English-language automotive speech recognition.

Speech-to-text workflows in vehicles: The source material places Nova-2 Automotive within Deepgram’s speech-to-text model line and ties it to automotive use, making vehicle-focused transcription the clearest documented fit.

How to use Nova-2 Automotive API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to deepgram/nova-2-automotive.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v1/stt/create",
    headers=headers,
    json={
      "model": "deepgram/nova-2-automotive",
      "url": "https://example.com/audio.mp3"
    },
).json()
gid = job["generation_id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v1/stt/{gid}", headers=headers).json()
    if res.get("status") in ("completed", "error", "failed"):
        break
    time.sleep(3)
print(res)

const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v1/stt/create", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "deepgram/nova-2-automotive",
    "url": "https://example.com/audio.mp3"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 3000));
  res = await (await fetch(`https://api.aimlapi.com/v1/stt/${job.generation_id}`, { headers })).json();
} while (!["completed", "error", "failed"].includes(res.status));
console.log(res);

# submit the job — the response contains "generation_id"
curl -X POST https://api.aimlapi.com/v1/stt/create \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepgram/nova-2-automotive","url":"https://example.com/audio.mp3"}'

# then poll for the result until it is ready
curl "https://api.aimlapi.com/v1/stt/{generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.