Run a model from Node.js Run a model from Google Colab Run a model from Python Fine-tune an image model

Build a website with Next.js Build a Discord bot with Python Build an app with SwiftUI Push your own model Push a Diffusers model Push a Transformers model Push a model using GitHub Actions Deploy a custom model Fine-tune a language model Get a GPU machine

Turn speech to text with WhisperX Run WhisperX with an API

How does Replicate work?Client libraries HTTP API Open source

Home / Guides

Turn speech to text with WhisperX

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.