VOICE · CALL · CUSTOM CHARACTER
WebCall
@YOLANYL
Open the web page and talk to your AI companion you set like making a phone call.
WebCall combines speaking, understanding and voice replying in the browser into one phone call. You can deploy it yourself, set up your AI companion's role, model and voice, and manage login accounts and usage.
Project address (can be copied to AI):https://github.com/YolanYL/webcall
PROJECT INTRO
Project introduction
WebCall is a set of self-deployable AI real-time voice call web pages. You speak in the browser, the system converts the sound into text and gives it to the model, and then synthesizes the answer into speech and plays it out.
It supports custom roles, multiple OpenAI compatible models, MiniMax speech, and multiple speech recognition schemes. The web wizard can be used to complete the configuration when starting for the first time, and comes with basic account, usage and management functions.
- Suitable for:People who want to add a web phone portal to their AI companion and decide on their own characters, models and voices.
- Platform:Python Flask with a web frontend, deployable to Hugging Face Spaces or Docker.
- Usage:Deploy the service, follow the web wizard to configure the model, speech recognition and speech synthesis services, and then call through the browser.
- License:AGPL-3.0。
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...