Groq: Whisper Large V3
Model Overview
| Property | Value |
|---|---|
| Model ID | groq/whisper-large-v3 |
| Name | Whisper Large V3 |
| Provider | Groq / OpenAI |
Description
OpenAI's Whisper Large V3 speech-to-text model hosted on Groq for ultra-fast transcription. Supports multiple languages and audio formats.
Specifications
| Spec | Value |
|---|---|
| Context Window | 448 tokens (30 seconds audio) |
| Modality | Audio to Text |
| Languages | 100+ |
Pricing
| Type | Price |
|---|---|
| Audio | $0.111 per hour |
Capabilities
- Speech-to-Text: Yes
- Multilingual: Yes
- Fast Transcription: Yes
- Multiple Formats: Yes
Use Cases
Audio transcription, meeting notes, podcast transcription, voice interfaces.
Integration with LangMart
Gateway Support: Type 2 (Cloud), Type 3 (Self-hosted)
API Usage:
curl -X POST https://api.langmart.ai/v1/audio/transcriptions \
-H "Authorization: Bearer sk-your-api-key" \
-F file=@audio.mp3 \
-F model="groq/whisper-large-v3"
Related Models
- groq/whisper-large-v3-turbo - Faster version
- groq/playai-tts - Text-to-speech
Last Updated: December 28, 2025