percept-speaker-id
por jarvis563
Coding Agents & IDEsResumen
Speaker identification and management for multi-person conversations.
Descripción
Qué hace esta skill
Tracks speaker identity in multi-person conversations by mapping anonymous speaker labels to real names. Controls which speakers can trigger voice commands based on owner and approval status. Integrates with Omi pendant hardware to identify the primary wearer.
Combines hardware-based primary speaker detection with a configurable registry, avoiding the need for a fully automated voice recognition system while still supporting per-speaker authorization.
Cuándo usarla
- Attributing quotes to specific people in meeting transcripts
- Restricting voice command access to approved household members
- Reviewing who spoke when in a recorded multi-person session
- Setting up a new speaker profile after adding a household member
- Auditing which unknown speakers were present in a conversation
Flujo de trabajo de ejemplo
User asks: who said the last command?
- 1
Receive transcript segment with SPEAKER_01 label from Omi
- 2
Look up SPEAKER_01 in percept/data/speakers.json
- 3
Resolve label to name 'Rob' with approved status
- 4
Check authorization level to confirm command was valid
- 5
Return speaker-attributed transcript entry
'Rob' triggered the command at [timestamp], authorized as an approved speaker
Requisitos
- Omi pendant device
- percept-listen skill installed and running
Instalación
clawhub install jarvis563/percept-speaker-idEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.