Name: Whisper Large API
Brand: Deepgram

Overview

What is Whisper Large API?

Whisper: Multilingual speech recognition model, robust, versatile, open-source.

Technical Specifications
- Supported inputs: Audio
- Output: Text

Performance Benchmarks
[embed]

Whisper Large API Pricing
- Pricing on request

Where to Use Whisper Large

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

Captioning and indexing
Generate subtitles and make audio archives searchable.

Uptime and performance

End-to-end latency (24h median): 310.5s

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Deepgram Whisper Large is documented for pre-recorded transcription, including through Deepgram’s Hosted API or on-prem deployments.

It is also suited to long audio files, with Deepgram’s docs stating that long audio files are supported up to a maximum of 20 minutes of processing time.

Deepgram’s materials describe it as supporting transcription features such as diarization, word-level timestamps, language detection, redaction, smart formatting, punctuation and numeral formatting, multichannel support, summarization, and topic detection.

Deepgram also presents Whisper Large as applicable to speech recognition across the list of supported languages in OpenAI’s Whisper model family.

How to use Whisper Large API

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

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v1/stt/create",
    headers=headers,
    json={
      "model": "deepgram/whisper-large",
      "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/whisper-large",
    "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/whisper-large","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.