WhisperFastUltra

Incredibly Fast Whisper

Whisper large-v3 optimized for speed (38M+ runs) — transcribes roughly 150 minutes of audio in under 100 seconds using batched inference. Chunk-level or word-level timestamps.

10 credits

per run

~150 minutes of audio transcribed in under 100 seconds

Whisper large-v3 accuracy

Chunk or word-level timestamps

Transcribe or translate task modes

Batched inference with adjustable batch size

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "vaibhavs10/incredibly-fast-whisper",
  "input": {
    "audio": "https://example.com/podcast-episode.mp3",
    "task": "transcribe",
    "timestamp": "word"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`audio`	string	Yes	-	Audio file to transcribe
`task`	string	No	transcribe	transcribe (same language) or translate (to English) transcribetranslate
`language`	string	No	None	Language of the audio ('None' auto-detects; 'korean' for Korean) Noneafrikaansalbanianamharicarabicarmenianassameseazerbaijanibashkirbasquebelarusianbengalibosnianbretonbulgariancantonesecatalanchinesecroatianczechdanishdutchenglishestonianfaroesefinnishfrenchgaliciangeorgiangermangreekgujaratihaitian creolehausahawaiianhebrewhindihungarianicelandicindonesianitalianjapanesejavanesekannadakazakhkhmerkoreanlaolatinlatvianlingalalithuanianluxembourgishmacedonianmalagasymalaymalayalammaltesemaorimarathimongolianmyanmarnepalinorwegiannynorskoccitanpashtopersianpolishportuguesepunjabiromanianrussiansanskritserbianshonasindhisinhalaslovaksloveniansomalispanishsundaneseswahiliswedishtagalogtajiktamiltatarteluguthaitibetanturkishturkmenukrainianurduuzbekvietnamesewelshyiddishyoruba
`batch_size`	integer	No	24	Parallel batches. Reduce if you hit memory errors
`timestamp`	string	No	chunk	Chunk-level or word-level timestamps chunkword
`diarise_audio`	boolean	No	false	Use Pyannote.audio to diarise the audio clips. You will need to provide hf_token below too.
`hf_token`	string	No	-	Provide a hf.co/settings/token for Pyannote.audio to diarise the audio clips. You need to agree to the terms in 'https://huggingface.co/pyannote/speaker-diarization-3.1' and 'https://huggingface.co/pyannote/segmentation-3.0' first.

How to Provide File Input

There are 3 ways to provide files for the audio parameter:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=vaibhavs10/incredibly-fast-whisper" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:audio=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "vaibhavs10/incredibly-fast-whisper",
  "input": {
    "prompt": "your prompt here",
    "audio": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Fast Podcast Transcription

Transcribe a long recording with word timestamps

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "vaibhavs10/incredibly-fast-whisper",
  "input": {
    "audio": "https://example.com/podcast-episode.mp3",
    "task": "transcribe",
    "timestamp": "word"
  }
}'