Whisper large-v3

The OpenAI Whisper large-v3 is a state-of-the-art model for automatic speech recognition (ASR) and speech translation.

Model ID

whisper-large-v3

Source

Hugging Face

Modality

• Input: Audio (e.g., .mp3, .mp4, .wav)
• Output: Text

Endpoints

• /v1/audio/transcriptions
• /v1/audio/translations

Rate limits

The effective rate limit for the Free and Standard tier is 25 MB/minute. The effective monthly quota for the Free tier is 100 MB/month.