OpenAI: Whisper Large V3
OpenAI's open speech recognition model. Transcribes audio in around 100 languages and is billed per second of audio.
- Maker
- OpenAI
- Model ID
openai/whisper-large-v3- Input
- audio
- Output
- transcription
Providers
- OVHcloud: Data centers: France; Sovereign EU; Zero data retention
- IONOS: Data centers: Germany; Sovereign EU; Zero data retention
- Scaleway: Data centers: France; Sovereign EU
- TensorX: Data centers: Ireland and Finland; Zero data retention
Facts as Markdown · Quickstart
More models by OpenAI
- OpenAI: GPT OSS 120b OpenAI · 131,072 tokens · text
More Transcription models
- Mistral AI: Voxtral Mini Transcribe 3 0 Mistral AI · transcription
- Mistral AI: Voxtral Small Transcribe 3 0 Mistral AI · transcription