Video Transcribe

whisperx-video-transcribe

Transform videos into accurate, text-based transcripts effortlessly with Video Transcribe

T4 16GB

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~35 sec

StatusActive

Version

0.0.1

Updatedabout 1 month ago

API Reference

View Full Documentation

Prerequisites

Create an API Key from the Eachlabs Console
Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time

API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}

def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "whisperx-video-transcribe",
            "version": "0.0.1",
            "input": {
  "url": "your url here",
  "debug": false,
  "batch_size": "16"
}
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

The API uses a two-step process: create prediction and poll for results
Response time: ~35 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion

Overview

WhisperX is an advanced transcription model designed for video and audio processing. Developed by adidoes, this model leverages cutting-edge AI to provide accurate, efficient, and context-aware transcriptions. Its capabilities extend beyond basic transcription, including speaker identification and timestamping, making it a powerful model for multimedia content creators and analysts.

Technical Specifications

Architecture: Built on the Whisper architecture with enhancements for real-time processing and multi-language support.
Speaker Diarization: Identifies and labels multiple speakers in audio, aiding in meeting transcription and interview analysis.
Timestamping: Generates precise timestamps for each segment of the transcription, enabling easy navigation and editing.

Key Considerations

Audio Quality: Background noise, overlapping speech, or low-quality recordings can affect transcription accuracy.
Language Accuracy: While the model is proficient in multiple languages, certain dialects or rare languages may yield less accurate results.

Tips & Tricks

Audio Quality:
- For best results, use clear, high-quality audio files with minimal background noise.
- Pre-process noisy or distorted audio to improve transcription accuracy.
Timestamps:
- Ensure the audio has consistent pacing for accurate timestamp alignment.

Capabilities

Accurate Transcription: Provides high-quality transcriptions with minimal errors for clear audio sources.
Speaker Labeling: Identifies and tags individual speakers, aiding in multi-speaker content analysis.

What can I use for?

Meeting Transcriptions: Record and transcribe meetings or interviews for easy documentation and review.
Podcast Summaries: Convert podcast audio into text for blog posts, summaries, or SEO optimization.

Things to be aware of

Podcast and Interview Transcription:
- Convert audio content into searchable, editable text for archiving or publication.
Academic and Market Research:
- Transcribe focus groups, interviews, or lectures for data analysis and reporting.
Language Practice and Learning:
- Use transcriptions to study pronunciation, grammar, and vocabulary in real-world contexts.

Limitations

Background Noise Sensitivity: The model may struggle with heavily distorted or noisy audio sources.
Complex Speaker Overlap: In scenarios with multiple speakers talking simultaneously, diarization may not be fully accurate.

Output Format: Text

Related AI Models

Incredibly Fast Fhisper

incredibly-fast-whisper

Voice to Text