WanderingAstronomer/Vociferous
Vociferous captures audio from your microphone, transcribes it in real-time using faster-whisper (CTranslate2 Whisper backend), and optionally refines the output with a local Small Language Model powered by CTranslate2.
Vociferous is a desktop application that helps individuals transform their spoken thoughts into written text quickly and efficiently. It takes audio input from your microphone or existing audio files, transcribes it in real-time, and can refine the text using local AI for improved grammar and clarity. This tool is ideal for writers, students, or anyone who brainstorms verbally and wants to capture ideas faster than typing.
Use this if you frequently dictate notes, drafts, or ideas and need an offline, secure, and customizable way to convert speech to polished text.
Not ideal if you primarily need to transcribe pre-recorded interviews or meetings with multiple speakers, as its focus is on individual dictation and refinement.
Stars
13
Forks
4
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/WanderingAstronomer/Vociferous"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
collabora/WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Kieirra/murmure
Fully local, private and cross platform Speech-to-Text with LLM Post-processing
Softcatala/whisper-ctranslate2
Whisper command line client compatible with original OpenAI client based on CTranslate2.
pavelzbornik/whisperX-FastAPI
FastAPI service on top of WhisperX
royshil/obs-localvocal
OBS plugin for local speech recognition and captioning using AI