# Incredibly Fast Whisper

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

- **Provider**: replicate
- **Model ID**: vaibhavs10/incredibly-fast-whisper
- **Category**: speech_to_text
- **Credits**: 10 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `hf_token` (string, optional): 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.
- `task` (string, optional): Task to perform: transcribe or translate to another language. (Default: `transcribe`; Options: `transcribe`, `translate`)
- `batch_size` (integer, optional): Number of parallel batches you want to compute. Reduce if you face OOMs. (Default: `24`)
- `diarise_audio` (boolean, optional): Use Pyannote.audio to diarise the audio clips. You will need to provide hf_token below too. (Default: `False`)
- `language` (string, optional): Language spoken in the audio, specify 'None' to perform language detection. (Default: `None`; Options: `None`, `afrikaans`, `albanian`, `amharic`, `arabic`, `armenian`, `assamese`, `azerbaijani`, `bashkir`, `basque`, `belarusian`, `bengali`, `bosnian`, `breton`, `bulgarian`, `cantonese`, `catalan`, `chinese`, `croatian`, `czech`, `danish`, `dutch`, `english`, `estonian`, `faroese`, `finnish`, `french`, `galician`, `georgian`, `german`, `greek`, `gujarati`, `haitian creole`, `hausa`, `hawaiian`, `hebrew`, `hindi`, `hungarian`, `icelandic`, `indonesian`, `italian`, `japanese`, `javanese`, `kannada`, `kazakh`, `khmer`, `korean`, `lao`, `latin`, `latvian`, `lingala`, `lithuanian`, `luxembourgish`, `macedonian`, `malagasy`, `malay`, `malayalam`, `maltese`, `maori`, `marathi`, `mongolian`, `myanmar`, `nepali`, `norwegian`, `nynorsk`, `occitan`, `pashto`, `persian`, `polish`, `portuguese`, `punjabi`, `romanian`, `russian`, `sanskrit`, `serbian`, `shona`, `sindhi`, `sinhala`, `slovak`, `slovenian`, `somali`, `spanish`, `sundanese`, `swahili`, `swedish`, `tagalog`, `tajik`, `tamil`, `tatar`, `telugu`, `thai`, `tibetan`, `turkish`, `turkmen`, `ukrainian`, `urdu`, `uzbek`, `vietnamese`, `welsh`, `yiddish`, `yoruba`)
- `audio` (string, **required**): Audio file
- `timestamp` (string, optional): Whisper supports both chunked as well as word level timestamps. (Default: `chunk`; Options: `chunk`, `word`)

## Example Request

```json
{
  "model": "vaibhavs10/incredibly-fast-whisper",
  "input": {
    "task": "transcribe",
    "audio": "https://replicate.delivery/pbxt/Js2Fgx9MSOCzdTnzHQLJXj7abLp3JLIG3iqdsYXV24tHIdk8/OSR_uk_000_0050_8k.wav",
    "batch_size": 64,
    "return_timestamps": true
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

json

## Tags

speech-to-text, transcription, whisper, fast, timestamps, multilingual

## Documentation

https://replicate.com/vaibhavs10/incredibly-fast-whisper