Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/platelminto/chatgpt-conversation
Have a conversation with ChatGPT using your voice, and have it talk back.
https://github.com/platelminto/chatgpt-conversation
Last synced: about 2 months ago
JSON representation
Have a conversation with ChatGPT using your voice, and have it talk back.
- Host: GitHub
- URL: https://github.com/platelminto/chatgpt-conversation
- Owner: platelminto
- License: mit
- Created: 2022-12-04T22:36:18.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2022-12-06T09:19:40.000Z (about 2 years ago)
- Last Synced: 2024-08-01T00:39:25.842Z (4 months ago)
- Language: Python
- Size: 7.81 KB
- Stars: 657
- Watchers: 20
- Forks: 73
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-chatgpt-tools - Voice-based chatGPT
- awesome-open-gpt - chatgpt-conversation
- awesome-chatgpt - chatgpt-conversation - Have a conversation with ChatGPT. (CLI tools / Examples)
- awesome-chatgpt - ChatGPT-conversation: talk to ChatGPT using your voice
- fucking-awesome-chatgpt - Voice-based chatGPT
- awesome-chatgpt - Voice-based chatGPT
- awesome-chatgpt - Voice interaction
- StarryDivineSky - platelminto/chatgpt-conversation
- awesome-chatgpt-zh - 基于语音的 chatGPT
- awesome-chatgpt - chatgpt-conversation - Have a conversation with ChatGPT. (CLI tools / Examples)
- awesome-chatgpt - platelminto/chatgpt-conversation - Have a conversation with ChatGPT using your voice, and have it talk back. (UIs / Other UIs)
- Awesome-ChatGPT - Voice-based chatGPT
- awesome-gpt - Voice-based chatGPT
- awesome-chatgpt - chatgpt-conversation
- awesome-ChatGPT-resource-zh - chatgpt-conversation: 用声音与 ChatGPT 对话,并让其回应
- awesome-chatgpt - chatgpt-conversation
README
# chatgpt-conversation
Have a conversation with ChatGPT using your voice, and have it talk back.## Requirements (Ubuntu)
- `espeak`
- `ffmpeg`
- `portaudio19-dev`
- `python3-pyaudio`To install all of them:
`sudo apt install portaudio19-dev python3-pyaudio ffmpeg espeak`
## Installation
Copy `config.json.example` to `config.json` and fill in the `session_token` value following the guide [here](https://github.com/acheong08/ChatGPT).
Also, install requirements:
`pip install -r requirements.txt`
## Usage
Run `chatgpt.py`, and wait 2 seconds before starting the conversation (this is to normalise ambient noise). You can keep responding to ChatGPT, it's all 1 "conversation".
## Next steps
- [ ] Cut-off ChatGPT as it's speaking if you decide to interrupt.
- [ ] Silence PyAudio errors.
- [ ] Remove common, useless end phrases from ChatGPT ("I am an online LLM...", etc.).
- [ ] Make this as a web-app (better text-to-speech, universal):
- [ ] Create interface
- [ ] Create backend
- [ ] Hook-up to a GPU so it's faster (in the speech->text bit).