Reverse Dependencies of vosk

The following projects have a declared dependency on vosk:

• anaouder — Breton language speech-to-text tools
• artbox — ArtBox is a tool set for handling multimedia files.
• ASRscsvmv — This package recognizes and translates your words
• audio-curation — Some scripts for checking and curating audio file contributions to the Mahabharata audio project.
• auto-caption — Automatic captioning.
• bro-listen — Interact with openAI API with voice
• come-again-question-mark — Transcription tool for video or audio to text
• comeagainquestionmark — Transcription tool for video to text
• jarvis-toolkit — Jarvis Toolkit
• localstack — LocalStack - A fully functional local Cloud stack
• mahnamahna — Media (text/audio/video) analysis and manipulation
• neweraai — NewEraAI - New Era Artificial Intelligence
• openav — OpenAV
• ovos-stt-plugin-vosk — A vosk stt plugin for mycroft
• ovos-ww-plugin-vosk — Kaldi wake word plugin for mycroft
• phonegpt — Make interactive phone call, using Twilio and OpenAI
• python-voice-assistant — Create your own voice assistant like jarvis
• pytranscript — CLI to transcript and translate audio and video files
• qedit — A CLI for automatically editing videos using word detection
• rcute-ai — Simple wrapper over some python libs for image/audio detection/recognition etc
• speech_user_interface — A universal speech user interface for wrapping applications to provide them with a user interface that uses speech rather than text commands or traditional user interfaces
• SpeechFast — Transcriber audio/video to text
• stark-engine — S.T.A.R.K - Speech and Text Algorithmic Recognition Kit. Modern framework for creating powerfull voice assistants.
• voice-commands — Allows mapping commands to your voice
• voice-stream — A streaming library for creating voice bots using LLMs. Connects LLMs to speech recognition and speech synthesis APIs.
• vosk-cli — A command line interface for Vosk. It generates subtitles (WebVTT files) from video and audio sources.
• voskIntentVoiceConvertHanzi — Offline open source speech recognition API based on Kaldi and Vosk