When using the AI Earbuds for call transcription or call translation, the system establishes two separate transcription channels simultaneously:
- One channel captures and transcribes your voice.
- The second channel captures and transcribes the other party’s voice.
Because both audio streams are processed independently in real time, this setup consumes double transcription minutes compared to standard single-channel recording.
For example:
- A 10-minute phone call using transcription or translation will deduct approximately 20 minutes of transcription time from your account.
This dual-channel processing is necessary to ensure accurate speaker recognition, real-time transcription, and translation quality during calls.