VOICE IDENTITY · FAMILIARITY · CONTEXT
voice-familiarity
VOICE-FAMILIARITY · @AKINIA0315
Ask your partner to tell whether the person speaking is the owner, an acquaintance, or an unknown person.
Voice-familiarity provides small-scale, consent-based speaker recognition for home companion machines, allowing the same sentence to be connected to the correct relationships and memories.
Project address (can be copied to AI):https://github.com/akinia0315/voice-familiarity
PROJECT INTRO
Project introduction
voice-familiarity locally builds a voiceprint embedding for a host and a small number of agreed acquaintances, returning matched, likely, unknown, or ambiguous for the conversation model to select titles, relationships, and memories.
It is not responsible for speech transcription, nor can it be used for login, door locking, payment, surveillance, or stranger retrieval. Any recognition failure should not block normal conversation.
- Suitable for:Voice scenarios for home companion devices and a small number of fixed relationships.
- Platform:Native Python component, replaceable model backend.
- Usage:With consent, a small number of voiceprints are recorded, and the recognition results are used as conversation context rather than authentication conclusions.
- License:Apache-2.0。
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...