Skip to main content
This is unreleased documentation for Haystack Documentation 3.1-unstable version.
For up-to-date documentation, see the latest version (3.0).
Version: 3.1-unstable

Audio

Use these components to work with audio in Haystack by transcribing files or converting text to audio.

NameDescription
FunASRTranscriberTranscribe audio files using FunASR — a local, open-source speech recognition toolkit supporting 50+ languages.
LocalWhisperTranscriberTranscribe audio files using OpenAI's Whisper model using your local installation of Whisper.
RemoteWhisperTranscriberTranscribe audio files using OpenAI's Whisper model.
Morty Proxy This is a proxified and sanitized view of the page, visit original site.