Whisper Large V3
by OpenAI
Industry-leading speech-to-text with multilingual support.
Parameters
1.5B
Context Length
30s
Category
audio
Available Serverless
Run queries immediately, pay only for usage
$0.006in|$0.006out
Per 1M Tokens
About this model
Whisper Large V3 is OpenAI's most capable speech recognition model, trained on 680,000 hours of multilingual audio data. It supports transcription and translation for 99 languages with high accuracy, even in noisy environments or with accented speech.
Capabilities
TranscriptionTranslation99 LanguagesNoise RobustAccent Recognition
Use Cases
- Meeting Transcription
- Podcast Processing
- Voice Assistants
- Subtitle Generation
Model Details
- Provider
- OpenAI
- Model ID
- openai/whisper-large-v3
- Parameters
- 1.5B
- Context Length
- 30s tokens
- Category
- audio
API Usage
Use the DOS API to integrate Whisper Large V3 into your applications. Our API is compatible with OpenAI's client libraries for easy migration.
Model ID
openai/whisper-large-v3Python
python
from dos import DOS
client = DOS()
response = client.chat.completions.create(
model="openai/whisper-large-v3",
messages=[
{"role": "user", "content": "Hello, how are you?"}
]
)
print(response.choices[0].message.content)cURL
bash
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/whisper-large-v3",
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}'Node.js
javascript
import DOS from 'dos-ai';
const client = new DOS();
const response = await client.chat.completions.create({
model: "openai/whisper-large-v3",
messages: [
{ role: "user", content: "Hello, how are you?" }
]
});
console.log(response.choices[0].message.content);