Voice Memo

Why It Exists

Users need to capture, search, and act on voice content from meetings, interviews, lectures, and personal notes without cloud-based transcription services.

How It Works

Lenovo Voice Memo is an AI-powered voice recording app for Lenovo AI Now PCs. Using on-device NPU processing, the system records audio, transcribes speech, generates summaries, and organizes memos automatically. The AI can identify speakers, detect action items, translate content, and sync with calendar events. All processing happens locally on the device, ensuring privacy for personal and professional recordings.

Everyday Use Cases

• Voice recording
• Speech transcription
• Memo summarization
• Action item extraction
• Speaker identification
• Translation
• Searchable memos

User Workflow

• User starts recording in Voice Memo
• Audio is captured with quality optimization
• AI transcribes speech in real-time using NPU
• System generates summary and identifies action items
• Memo is organized and searchable

AI Processing Flow

Audio is captured by device microphones and processed by on-device NPU speech models. Speaker diarization separates voices. Transcription runs in real-time using neural models. Summarization uses AI to extract key points. Translation is available for supported language pairs. All content is stored encrypted locally.

Inputs / Outputs

Inputs:

• Voice recordings
• Speaker identification
• Timestamp data
• Language settings
• User tags and categories
• Calendar integration

Outputs:

• Transcribed text
• Searchable memos
• Action items
• Summaries
• Translated content
• Tagged recordings
• Synced calendar events

Known Limitations

• Accuracy varies with audio quality and accents
• Limited languages for on-device transcription
• Background noise reduces quality
• Speaker identification needs 3+ voices minimum

Unsupported Scenarios

• Multi-language transcription
• Voice command search
• Export to cloud services
• Integration with calendar
• Batch transcription
• Voice tag filtering

Performance Notes

Real-time transcription in under 200ms latency; Summary generation in under 5 seconds; NPU processing power usage under 4 percent per hour; Supports 10 languages; Offline mode available

Available On

Shows where this feature is available and how its AI processing works on each platform. Availability may vary by device.

Research Status

Confidence and verification reflect how complete documentation is. Fields may show Not assessed or Not yet verified while research is ongoing - this flags gaps, not product deficiencies.

Research Notes

Available on Lenovo AI Now PCs with Snapdragon X or Intel Lunar Lake; Requires Lenovo Voice Memo app; Windows 11 with NPU support; Introduced 2024

Details

Capability Mapping

This feature maps to canonical capability family: Translation.

Canonical capability: Message Translation.

• Message Translation - Translates text messages between languages.

Grounded in 1 device(s) on Lenovo AI Now.