DocumentationAPI Reference📓 Tutorials🧑‍🍳 Cookbook🤝 Integrations💜 Discord


Use LocalWhisperTranscriber to transcribe audio files using OpenAI's Whisper model using your local installation of Whisper.

Folder path/audio/
Most common position in a pipelineAs the first component in an indexing pipeline
Mandatory input variables“audio_files”: A list of paths or binary streams that you want to transcribe
Output variables“documents”: A list of documents


The component also needs to know which Whisper model to work with. Specify this in the model parameter when initializing the component. All transcription is completed on the executing machine, and the audio is never sent to a third-party provider.

See other optional parameters you can specify in our API documentation.

See the Whisper API documentation and the official Whisper GitHub repo for the supported audio formats and languages.

To work with the LocalWhisperTranscriber, install torch and Whisper first with the following commands:

pip install 'transformers[torch]'
pip install -U openai-whisper


On its own

Here’s an example of how to use LocalWhisperTranscriber on its own:

import requests
from import LocalWhisperTranscriber

response = requests.get("")
with open("kennedy_speech.mp3", "wb") as file:

transcriber = LocalWhisperTranscriber(model="tiny")

transcription =["./kennedy_speech.mp3"])

In a pipeline

The pipeline below fetches an audio file from a specified URL and transcribes it. It first retrieves the audio file using LinkContentFetcher, then transcribes the audio into text with LocalWhisperTranscriber, and finally outputs the transcription text.

from import LocalWhisperTranscriber
from haystack.components.fetchers import LinkContentFetcher
from haystack import Pipeline

pipe = Pipeline()
pipe.add_component("fetcher", LinkContentFetcher())
pipe.add_component("transcriber", LocalWhisperTranscriber(model="tiny"))

pipe.connect("fetcher", "transcriber")
result =
    data={"fetcher": {"urls": [""]}})

Related Links

See the parameters details in our API reference: