Whisper Small API

deepgram/whisper-small
Whisper: Multilingual speech recognition model, robust, versatile, open-source.
Output
$0.00008233 / sec
Released
Dec 30, 2025

How to use Whisper Small API

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

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

Whisper Small API Pricing

TypePrice
Output
$0.00008233 / sec

Whisper Small Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
LibriSpeech WER
3.432
Word Error Rate on read English speech (lower better)SourceSeptember 21, 2026
Common Voice WER
87.300
WER on crowdsourced multilingual speechSourceSeptember 21, 2026

Whisper Small vs other models

ModelInputOutputContextBest for
Whisper Small
This page
$0.00008233 / sec
Transcription
$130 / 1M characters
$130 / 1M
Speech synthesis
$130 / 1M characters
$0.13 / 1M tokens
Speech synthesis
$78 / 1M characters
$0.078 / 1M tokens
Speech synthesis
$13 / 1M characters
$0.013 / 1M tokens
Speech synthesis

Frequently asked questions

Whisper Small takes audio as input and returns text.

Whisper Small became available on December 30, 2025.

Whisper Small is priced at output $0.00008233 / sec.

Whisper Small was built by Deepgram.

Use deepgram/whisper-small as the model id on AI/ML API.

Yes. Whisper Small is served through AI/ML API, so the same key and endpoint format used for other models applies.

Yes, it is a multilingual speech recognition model, according to its description.

Start building with Whisper Small

Get API Key
1000+ models, one API.