Nova-2 Meeting API

deepgram/nova-2-meeting
Nova-2: Advanced, versatile ASR model for diverse transcription needs.
Output
$0.000071667 / sec
Released
Dec 30, 2025

Overview

What is Nova-2 Meeting API?

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

Technical Specifications
- Supported inputs: Audio
- Output: Text

Performance Benchmarks
[embed]

Nova-2 Meeting API Pricing
- Pricing on request

Where to Use Nova-2 Meeting

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

Captioning and indexing
Generate subtitles and make audio archives searchable.

Use cases

Optimized for conference room settings with multiple speakers sharing a single microphone. This makes it suitable for meeting transcription in conference rooms.

Documented as a fit for meeting-minute pipelines and cost-capped meeting summarization workflows, especially for bulk captioning and daily meeting dumps.

It is also listed as optimized for meetings, indicating use in general meeting transcription workflows.

How to use Nova-2 Meeting API

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

Nova-2 Meeting API Pricing

TypePrice
Output
$0.000071667 / sec

Nova-2 Meeting vs other models

ModelInputOutputContextBest for
$0.000071667 / sec
Transcription
$100 / 1M characters
$130 / 1M
Speech synthesis
$100 / 1M characters
$0.13 / 1M tokens
Speech synthesis
$60 / 1M characters
$0.078 / 1M tokens
Speech synthesis
$10 / 1M characters
$0.013 / 1M tokens
Speech synthesis

Frequently asked questions

Nova-2 Meeting takes audio as input and returns text.

Nova-2 Meeting became available on December 30, 2025.

Nova-2 Meeting is priced at output $0.00009317 / sec.

Nova-2 Meeting was built by Deepgram.

Use deepgram/nova-2-meeting as the model id on AI/ML API.

Yes. Nova-2 Meeting is served through AI/ML API, so the same key and endpoint format used for other models applies.

It is an advanced, versatile ASR model designed for diverse transcription needs.

Its model id is deepgram/nova-2-meeting.

Start building with Nova-2 Meeting

Get API Key
1000+ models, one API.