Whisper overview
Whisper specs
- Model ID
deepgram/whisper-large- 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 Large 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 meetings, interviews, and conference calls
- Voice search and voice command systems
- Multilingual speech recognition and translation apps
- Customer support call transcription and analysis
- Legal and medical transcription services
- Podcast and audio content indexing
- Market research from customer call analysis
- Accessible voice interfaces and subtitles generation
How to use the Whisper 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-large"
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "deepgram/whisper-large"
}
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-large"
}),
});
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
Related articles
-1%20(1).webp)
Whisper FAQ
What inputs and outputs does Whisper support?
Whisper takes audio as input and returns text.
When was Whisper released?
Whisper became available on September 21, 2022.
How much does Whisper cost?
Whisper is priced at output $0.000104 / sec.
Who created Whisper?
Whisper was built by OpenAI.
How do I call Whisper on AI/ML API?
Send a request to v1/stt with deepgram/whisper-large as the model id.
Is Whisper available through a single API key?
Yes. Whisper is served through AI/ML API, so the same key and endpoint format used for other models applies.
What is the Whisper model ID?
Use deepgram/whisper-large as the model parameter. Requests go to https://api.aimlapi.com/v1/stt/create with your AI/ML API key.