Whisper Base overview
Whisper Base specs
- Model ID
deepgram/whisper-base- 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 Base 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
Whisper Base is a speech-to-text model available through Deepgram Whisper Cloud, with the model identifier whisper-base. It is suitable for transcribing recorded speech into text, such as meetings, interviews, lectures, and voice notes.
It can also be used for captioning spoken audio in media workflows, where audio content needs text output for display alongside video or live playback. Another direct use case is call or voicemail transcription, since Deepgram documents base-model variants for phonecall and voicemail transcription within its speech-to-text lineup.
How to use the Whisper Base API
View docs
Build 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-base"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "deepgram/whisper-base"
}
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-base"
}),
});
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.
Models similar to Whisper Base
Related articles
-1%20(1).webp)
Whisper Base FAQ
What inputs and outputs does Whisper Base support?
Whisper Base takes audio as input and returns text.
When was Whisper Base released?
Whisper Base became available on December 30, 2025.
How much does Whisper Base cost?
Whisper Base is priced at output $0.00007583 / sec.
Who created Whisper Base?
Whisper Base was built by Deepgram.
How do I call Whisper Base on AI/ML API?
Use deepgram/whisper-base as the model id on AI/ML API.
Is Whisper Base available through a single API key?
Yes. Whisper Base is served through AI/ML API, so the same key and endpoint format used for other models applies.
Does the Whisper Base model support multiple languages?
Yes, Whisper Base is described as a multilingual speech recognition model.
Is Whisper Base an open-source model?
Yes, Deepgram describes Whisper Base as an open-source speech recognition model.
What is the Whisper Base model ID?
Use deepgram/whisper-base as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.