Jaseci Speech Package (jac_speech)

The jac_speech package contains a collection of state-of-the-art Speech models that can be used to perform various speech tasks such as speech to text, text to speech etc. following is a list of all the models available in the jac_speech package.


Each module can be installed individually or all at once. To install all modules at once.

pip install jac_speech[all] # Installs all the modules present in the jac_speech package
pip install jac_speech[stt] # Installs the  stt module present in the jac_speech package
pip install jac_speech[stt,vc_tts] # Installs the stt and vc_tts module present in the jac_speech package

List of Models

ModuleModel TypeModel NameDocsTypeStatusDescriptionResources
sttSpeech to TextWhisperLinkNo Training req.Readytranscription or translation of a give audio sequence.Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI Whisper
vc_ttsText to SpeechCoquiLinkNo Training req.ReadyList of Amplitudes of the synthesized audio wav.


To load the jac_speech.stt package into jaseci in local environment, run the following command in the jsctl console.

jsctl > actions load module jac_speech.stt