Turn speech to text with WhisperX
Table of contents
WhisperX transcribes audio to text. It’s an accelerated version of OpenAI’s Whisper model.
With Replicate, you can run WhisperX in the cloud with one line of code.
Run WhisperX in our Playground
Want to try out WhisperX without writing code? Check out our WhisperX model playground.
Run WhipserX with an API
With Replicate, you can run WhisperX in the cloud with one line of code.
Run WhisperX with JavaScript
You can run WhisperX with our official JavaScript client:
npm install replicate
Set the REPLICATE_API_TOKEN
environment variable:
export REPLICATE_API_TOKEN=<your-api-token>
Import and set up the client:
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run daanelson/whisperx using Replicate’s API:
const output = await replicate.run(
"daanelson/whisperx:latest",
{
input: {
"audio": "https://replicate.delivery/pbxt/J5r78wKSymorzW9idAbbbJ7iXQl9GddZTwfdX5OlLJW2hLR2/OSR_uk_000_0050_8k.wav",
"debug": False,
"only_text": False,
"batch_size": 32,
"align_output": False
}
}
);
console.log(output);
Note that WhisperX takes an audio file as input. You can provide URLs and or base 64 strings here as values for the image.
To learn more, take a look at the guide on getting started with Node.js.
Run WhisperX with Python
You can run WhisperX with our official Python client:
pip install replicate
Set the REPLICATE_API_TOKEN
environment variable:
export REPLICATE_API_TOKEN=<your-api-token>
Run daanelson/whisperx using Replicate’s API:
import replicate
output = replicate.run(
"daanelson/whisperx:latest",
input={
"audio": "https://replicate.delivery/pbxt/J5r78wKSymorzW9idAbbbJ7iXQl9GddZTwfdX5OlLJW2hLR2/OSR_uk_000_0050_8k.wav",
"debug": False,
"only_text": False,
"batch_size": 32,
"align_output": False
}
)
print(output)
Note that WhisperX takes an audio file as input. You can provide URLs and or base 64 strings here as values for the image.
To learn more, take a look at the guide on getting started with Python.
Run WhisperX with cURL
You can call the HTTP API directly with tools like cURL:
Set the REPLICATE_API_TOKEN
environment variable:
export REPLICATE_API_TOKEN=<your-api-token>
Run daanelson/whisperx using Replicate’s API:
curl -s -X POST \
-H "Authorization: Token $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-d $'{
"version": "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd",
"input": {
"audio": "https://replicate.delivery/pbxt/J5r78wKSymorzW9idAbbbJ7iXQl9GddZTwfdX5OlLJW2hLR2/OSR_uk_000_0050_8k.wav",
"debug": False,
"only_text": False,
"batch_size": 32,
"align_output": False
}
}' \
https://api.replicate.com/v1/models/daanelson/whisperx/predictions
Note that WhisperX takes an audio file as input. You can provide URLs and or base 64 strings here as values for the image.
To learn more, take a look at Replicate’s HTTP API reference docs.
You can also run WhisperX using other Replicate client libraries for Golang, Swift, Elixir, and others