Name: Nova-2 Conversational AI API
Brand: Deepgram

Overview

What is Nova-2 Conversational AI API?

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

Technical Specifications
- Supported inputs: Audio
- Output: Text

Performance Benchmarks
[embed]

Nova-2 Conversational AI API Pricing
- Pricing on request

Where to Use Nova-2 Conversational AI

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

Captioning and indexing
Generate subtitles and make audio archives searchable.

Use cases

Optimized for human-to-bot interactions, including IVR systems, voice assistants, and automated kiosks.

It is documented for use in real-time transcription for conversational AI platforms and voicebot-style applications.

It is also described as suitable for environments where a human is talking to an automated bot, which includes automated customer interaction workflows.

A broader Deepgram description of Nova-2 links conversational AI use to responsive AI agents and conversational AI applications that exchange real-time information between humans and LLMs.

How to use Nova-2 Conversational AI API

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

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-conversationalai",
      "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-conversationalai",
    "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-conversationalai","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.