https://github.com/ashot72/speech-to-text-to-speech
Node.js app where you can ask questions to ChatGPT using voice prompts, see the ChatGPT-like word-by-word answer, and then listen to the responses with voice
https://github.com/ashot72/speech-to-text-to-speech
chatgpt gtts langchain large-language-models llm speech-to-text speech-to-text-to-speech text-to-speech whisper
Last synced: 3 months ago
JSON representation
Node.js app where you can ask questions to ChatGPT using voice prompts, see the ChatGPT-like word-by-word answer, and then listen to the responses with voice
- Host: GitHub
- URL: https://github.com/ashot72/speech-to-text-to-speech
- Owner: Ashot72
- Created: 2023-05-28T11:39:56.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-11-01T09:34:02.000Z (almost 2 years ago)
- Last Synced: 2024-11-08T03:23:42.989Z (11 months ago)
- Topics: chatgpt, gtts, langchain, large-language-models, llm, speech-to-text, speech-to-text-to-speech, text-to-speech, whisper
- Language: JavaScript
- Homepage:
- Size: 979 KB
- Stars: 8
- Watchers: 1
- Forks: 4
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Speech to Text to Speech
I built a Node.js app where you can ask questions to ChatGPT using voice prompts, see the ChatGPT-like word-by-word answer, and then listen to the responses with voice.
Voice to Text: I turn an audio into text using [Whisper](https://openai.com/research/whisper) which is an OpenAI Speech Recognition Model that turns audio
into text with up to 99% accuracy. Whisper is a speech transcription system form the creators of ChatGPT. Anyone can use it, and it is completely free. The system is trained on 680 000 hours of speech data from the network and recognizes 99 languages.
Generating Answers: To generate word-by-word answers and display them, we utilize the [LangChain](https://js.langchain.com/) streaming API . This API allows
us to receive words in real-time as they are generated. Additionally, we use Node.js Socket.IO, which enables bidirectional and event-based communication between the client and server.
Text to Voice: I use [gTTS.js](https://www.npmjs.com/package/gtts) which is Google Text to Speech JavaScript library originally written in Phyton.
To get started.
```
Clone the repository
git clone https://github.com/Ashot72/Speech-to-Text-to-Speech
cd Speech-to-Text-to-Speech
Add your key to .env file
# installs dependencies
npm install
# to run locally
npm start
```
Go to [Speech To Text to Speech Video](https://youtu.be/PZWEQjuDxog) page
Go to [Speech To Text to Speech Description](https://ashot72.github.io/Speech-to-Text-to-Speech/doc.html) page