There are 9 repositories under google-speech-to-text topic.
Python AI assistant 🧠
speech to text benchmark framework
🏷️ Mobile App that generates tags for post with ChatGPT and IA Voice Google.
A simple app that demostrates how to use the google-speech-to-text API for real time transcription with react and node js
Let AI create the notes of your Teams Meeting
Takes audio and reference transcriptions in bulk and generates WER
Edith Virtual Assistant 🧠
JARVIS-Personal_AI_Voice_Assistant
Keep your notes as a noise.
Detecting hate speech using the spoken content of videos using Machine Learning
Convert sound to text in PHP using Cloud Speech-to-Text of Google
A demo to show Speech Diarization (seperating audio of different speaker) and converting them to text using Google Cloud Speech API.
[🏆 Harm Reduction Category Winner, Top 5 @RUHacks] Drug-Venture Companion
Uses a Python script to transcribe an audio file and turn the transcription into a labeled signal set for use in MATLAB's AudioLabeler.
Base Engine for Google Transcription
Voice-driven VR Pokémon Unity game for Google Cardboard on iOS
Python Voice-Assistant
Proof of concept for transcribing podcasts into text using GCP Speech2Text service
A voice changer made using google's speech to text, and elevenlabs
Speech-to-text library that uses several Google APIs to transcribe Norwegian speech into text.
Spocode "spoken code" is an Intellij-plugin that enables java programmers to code by voice.
A Voice Assistant which performs searches, calculations, sends emails, captures photo, tells about the weather condition and reminds you of everything!!
TASS stands for Transcription Assistant Speech Recognition System
A very basic Telegram Bot that performs Speech-To-Text written in Node.js using Google Cloud APIs
TThis session is how a speech can be recognized by a computer and how a text can be transformed into a speech
Super flexible, custom voice mail and call routing for Twilio controlled by a Telegram bot control interface using Google Speech to Text
audio processing service for mock-buddy
:robot: Public Speaking algorithm that uses Google API to track speaker's facial movements and emotions. Winner of Google Cloud Platform API (LA Hacks 2019).
PHP package speech to text (audio, recordings) and make a summary.
Extracts the voice from the audio and transcribes it into text to find out what is being said.
Grounded Language Acquisition using crowd sourced data
Cancel your NYT subscription ❌ 🗞️