الانتقال إلى المحتوى الرئيسي

OpenAIAdded Jan 15, 2025Speech to textPrivateOpen weights

Whisper Large V3

Whisper Large V3 is OpenAI’s open-weight speech recognition model, trained on about 5 million hours of audio and able to transcribe around 100 languages. It’s a robust general-purpose choice for multilingual transcription.

openai/whisper-large-v3POST https://api.venice.ai/api/v1/audio/transcriptions
Per audio second
$0.0001
Per minute
$0.006
Per hour
$0.36
Per 1K minutes
$6.00
for batch planning

Pricing

USD per second of audio
1 second billed unit
$0.0001
1 minute
$0.006
1 hour
$0.36
1,000 minutes
$6.00

Specs

Model ID
openai/whisper-large-v3
Endpoint
POST /api/v1/audio/transcriptions
Added
Jan 15, 2025
Weights
Open
POST/api/v1/audio/transcriptions
curl https://api.venice.ai/api/v1/audio/transcriptions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-F model=openai/whisper-large-v3 \
-F file=@meeting.mp3

Privacy

Tier 1
Anonymized

Included

Tier 2 · this model
Private

Zero data retention, enforced by contract. Prompts and outputs aren’t stored.

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available