Whisper
by SoAI · Bundled
Local speech to text with OpenAI Whisper for audio transcription and translation, on CPU or accelerator builds that fit the host.
Whisper is a persistent local speech-to-text backend. It provides audio transcription and audio translation, can search for and download compatible models, and allows one active request at a time. It does not handle chat, completions, embeddings, images, or text to speech.
In SoAI, open Plugins > Whisper > Manage backend to choose a CPU or accelerator variant that matches the host and its drivers, then add a Whisper model from Models > Add model.
Version 1.0.2
Install from a file
In SoAI, open Plugins → Add plugin → Upload plugin and select the downloaded .soaiplugin file.
Install from a URL
Copy this URL, then open Plugins → Add plugin → Download plugin from URL in SoAI and paste it there.
https://soai.to/v1/whisper/1.0.2/874c71353faa19f5002177a3ed5b9a3944c3f9316240fa0858011e47c508849e/whisper.soaiplugin
SHA-256 checksum
874c71353faa19f5002177a3ed5b9a3944c3f9316240fa0858011e47c508849e
Previous versions 1
Version 1.0.1
Install from a file
In SoAI, open Plugins → Add plugin → Upload plugin and select the downloaded .soaiplugin file.
Install from a URL
Copy this URL, then open Plugins → Add plugin → Download plugin from URL in SoAI and paste it there.
https://soai.to/v1/whisper/1.0.1/32bc2e56dd14c9258e235d5dad6e637257cad09592c411f05f7268f2e0a3526c/whisper.soaiplugin
SHA-256 checksum
32bc2e56dd14c9258e235d5dad6e637257cad09592c411f05f7268f2e0a3526c