VOICE · LOCAL TRANSCRIPTION · TEXT
whisper.cpp
@GGML-ORG
Convert what you say into text directly on the device, so that the AI companion can understand the speech without uploading the recording.
After a human speaks or sends a recording, whisper.cpp will run Whisper on the current device to convert the sound into text. The companion front-end or chat model then reads these texts and responds, and the recording does not need to be uploaded to the cloud for recognition first.
Project address (can be copied to AI):https://github.com/ggml-org/whisper.cpp
PROJECT INTRO
Project introduction
whisper.cpp is a native speech-to-text engine that can be embedded in other projects. It receives a recording file or microphone sound, runs Whisper on the current device, and outputs the recognized text.
After giving these texts to your AI companion, he or she can reply based on what you say. Speech recognition can run offline on computers, mobile phones, Raspberry Pis and browsers, making it suitable for people who don't want to hand over recordings to the cloud for processing.
- Suitable for:People who want to add local voice input to AI companions, or need to organize recorded text offline.
- Input:Recording file or live microphone sound.
- Output:The recognized text can be passed on to chat models, subtitle systems or other applications.
- Usage:Install or compile whisper.cpp, download the compatible Whisper model, and then call the speech recognition capabilities by other applications.
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...