Battle-tested speech recognition. Widely deployed, well-supported, excellent accuracy.
2B
Parameters
N/A
Context Window
Open Source
License
Nov 6, 2023
Released
💰 Pricing
Input
$0.006/min
per 1M tokens
Output
N/A
per 1M tokens
⚡ Strengths
🎯 Use Cases
API Available
This model is accessible via API for integration into your applications.
🛠️ Tools Built on Whisper Large v3
Descript
Descript
AI-powered video/podcast editor. Edit video by editing text. Auto-transcription, filler word removal, eye contact.
Riverside
Riverside
AI-powered recording studio for podcasts and video. Local recording, transcription, and AI editing.
Replicate
Replicate
Run open-source models via API. One-line deployment for Llama, Flux, Whisper, and thousands more.
⭐ Related Models
GPT-5
OpenAI
OpenAI's latest flagship. Advanced multimodal capabilities with native tool use, improved reasoning, and massive knowledge.
GPT-4o
OpenAI
Omni model supporting text, vision, and audio natively. Fast and capable with strong multimodal understanding.
GPT-4o Mini
OpenAI
Compact and affordable. Surprisingly capable for its price point, ideal for high-volume applications.