Whisper Small overview
Whisper Small specs
- Model ID
deepgram/whisper-small- Developer
- Deepgram
- Input
- Audio
- Output
- Text
- Endpoint
POST https://api.aimlapi.com/v1/stt/create
Whisper: Multilingual speech recognition model, robust, versatile, open-source.
Whisper Small API Pricing
- Pricing on request
Transcription
Convert calls, meetings, and media into accurate, searchable text.
Captioning and indexing
Generate subtitles and make audio archives searchable.
Use cases
Transcription of prerecorded audio is explicitly supported for Deepgram Whisper Cloud, including whisper-small, with access through Deepgram’s Hosted API or on-prem deployments.
Language detection is documented among the supported transcription features for Deepgram Whisper Cloud models, including whisper-small.
Diarization is documented as a supported transcription feature for Deepgram Whisper Cloud models, including whisper-small.
Summarization is also listed among the supported transcription features for Deepgram Whisper Cloud models, including whisper-small.
How to use the Whisper Small API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/stt/create' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "deepgram/whisper-small"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "deepgram/whisper-small"
}
response = requests.post("https://api.aimlapi.com/v1/stt/create", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/stt/create", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "deepgram/whisper-small"
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());The request returns a generation id. Poll GET https://api.aimlapi.com/v1/stt/create?generation_id=<id> until the status is completed.
Related articles
Whisper Small FAQ
What inputs and outputs does Whisper Small support?
Whisper Small takes audio as input and returns text.
When was Whisper Small released?
Whisper Small became available on December 30, 2025.
How much does Whisper Small cost?
Whisper Small is priced at output $0.00008233 / sec.
Who created Whisper Small?
Whisper Small was built by Deepgram.
How do I call Whisper Small on AI/ML API?
Use deepgram/whisper-small as the model id on AI/ML API.
Is Whisper Small available through a single API key?
Yes. Whisper Small is served through AI/ML API, so the same key and endpoint format used for other models applies.
Is Whisper Small able to handle multiple languages?
Yes, it is a multilingual speech recognition model, according to its description.
What is the Whisper Small model ID?
Use deepgram/whisper-small as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.

-1%20(1).webp)
