Audio & Video Processing

# Ingest audio file (auto-transcribes)
memvid put memory.mv2 --input podcast.mp3

# Ingest multiple audio files
memvid put memory.mv2 --input ./recordings/

# With metadata
memvid put memory.mv2 --input interview.wav --metadata '{"speaker": "John Doe", "date": "2024-01-15"}'

# Specify language (faster, more accurate)
memvid put memory.mv2 --input audio.mp3 --language en

# Force language detection
memvid put memory.mv2 --input audio.mp3 --detect-language

# Use larger model for better accuracy
memvid put memory.mv2 --input audio.mp3 --whisper-model medium

# Install specific model
memvid models install whisper-medium

# Use installed model
memvid put memory.mv2 --input audio.mp3 --whisper-model medium

# English
memvid put memory.mv2 --input audio.mp3 --language en

# Spanish
memvid put memory.mv2 --input audio.mp3 --language es

# Mandarin Chinese
memvid put memory.mv2 --input audio.mp3 --language zh

# Auto-detect (slower)
memvid put memory.mv2 --input audio.mp3 --detect-language

# Ingest video (transcribes audio + extracts frames)
memvid put memory.mv2 --input meeting.mp4

# Video only (no audio transcription)
memvid put memory.mv2 --input silent-video.mp4 --no-transcribe

# Audio only (skip frame extraction)
memvid put memory.mv2 --input video.mp4 --audio-only

# Extract key frames for visual search
memvid put memory.mv2 --input video.mp4 --extract-frames

# Control frame density
memvid put memory.mv2 --input video.mp4 --frame-interval 30  # Every 30 seconds

# Extract specific number of frames
memvid put memory.mv2 --input video.mp4 --max-frames 50

# Enable visual embeddings for frames
memvid put memory.mv2 --input video.mp4 --clip-embeddings

# Search by visual content
memvid find memory.mv2 --query "person at whiteboard" --mode clip

# Search transcription text
memvid find memory.mv2 --query "quarterly revenue"

# Search with timestamp context
memvid find memory.mv2 --query "action items" --json

# Results include timecodes:
# {
#   "frame_id": "frame_abc123",
#   "text": "The action items from this meeting are...",
#   "timestamp": "00:15:32",
#   "source": "meeting.mp4"
# }

# Ask about audio/video content
memvid ask memory.mv2 --question "What were the main decisions from the meeting?"

# Get context with timestamps
memvid ask memory.mv2 --question "What did John say about the budget?" --sources

# Search by visual description
memvid find memory.mv2 --query "chart showing growth" --mode clip

# Combine text and visual
memvid find memory.mv2 --query "presentation slide" --mode auto

# Play entire audio
memvid view memory.mv2 --frame-id frame_abc --play

# Play specific segment
memvid view memory.mv2 --frame-id frame_abc --play --start-seconds 30 --end-seconds 60

# Play from timestamp
memvid view memory.mv2 --frame-id frame_abc --play --start-seconds 120

# Play video
memvid view memory.mv2 --frame-id frame_xyz --play

# Play segment
memvid view memory.mv2 --frame-id frame_xyz --play --start-seconds 0 --end-seconds 30

# Preview mode (thumbnail)
memvid view memory.mv2 --frame-id frame_xyz --preview

# Create meeting memory
memvid create meetings.mv2

# Ingest meeting recordings
memvid put meetings.mv2 --input ./recordings/ --language en

# Find specific discussions
memvid find meetings.mv2 --query "budget approval"

# Ask about decisions
memvid ask meetings.mv2 --question "What was decided about the Q4 budget?"

# Play the relevant segment
memvid view meetings.mv2 --frame-id frame_abc --play --start-seconds 1234

# Create podcast memory
memvid create podcasts.mv2

# Ingest episodes with metadata
memvid put podcasts.mv2 --input episode-42.mp3 \
  --metadata '{"show": "Tech Talk", "episode": 42, "guests": ["Alice", "Bob"]}'

# Search across all episodes
memvid find podcasts.mv2 --query "machine learning trends"

# Timeline of episodes
memvid timeline podcasts.mv2 --reverse

# Create tutorial library
memvid create tutorials.mv2

# Ingest with frame extraction
memvid put tutorials.mv2 --input ./tutorials/ --extract-frames --clip-embeddings

# Find by spoken content
memvid find tutorials.mv2 --query "how to configure webpack"

# Find by visual content
memvid find tutorials.mv2 --query "terminal with npm commands" --mode clip

# Create lecture memory
memvid create lectures.mv2

# Ingest lecture videos
memvid put lectures.mv2 --input ./cs101/ --whisper-model medium

# Search for topics
memvid find lectures.mv2 --query "binary search algorithm"

# Ask study questions
memvid ask lectures.mv2 --question "Explain the time complexity of quicksort"

# Create call memory
memvid create calls.mv2

# Ingest voicemails
memvid put calls.mv2 --input ./voicemails/ --metadata '{"type": "voicemail"}'

# Find by caller mention
memvid find calls.mv2 --query "callback number"

# Enrich with entity extraction
memvid enrich calls.mv2 --engine groq
memvid state calls.mv2 --entity "Customer Service"

# Install with Metal support
cargo install memvid-cli --features metal

# Or via Homebrew (includes Metal)
brew install memvid/tap/memvid

# Install with CUDA support
cargo install memvid-cli --features cuda

# Requires CUDA toolkit and cuDNN

# Process multiple files in parallel
memvid put memory.mv2 --input ./media/ --parallel-segments

# Limit concurrent transcriptions (manage memory)
memvid put memory.mv2 --input ./media/ --max-concurrent 2

# Ingest incrementally
memvid put memory.mv2 --input ./media/2024-01/
memvid put memory.mv2 --input ./media/2024-02/

# Check progress
memvid stats memory.mv2
memvid timeline memory.mv2 --limit 10

{
  "frame_id": "frame_abc123",
  "uri": "mv2://media/meeting.mp4",
  "content_type": "audio/transcript",
  "metadata": {
    "source_file": "meeting.mp4",
    "duration_seconds": 3600,
    "segment_start": 932.5,
    "segment_end": 945.2,
    "timestamp": "00:15:32",
    "language": "en",
    "confidence": 0.94,
    "whisper_model": "small"
  }
}

# View frame with metadata
memvid view memory.mv2 --frame-id frame_abc --json

# Filter by media type
memvid timeline memory.mv2 --filter "content_type:audio/transcript"

# Check if Whisper model is installed
memvid models list

# Install required model
memvid models install whisper-small

# Try with explicit language
memvid put memory.mv2 --input audio.mp3 --language en

# Use larger model
memvid put memory.mv2 --input audio.mp3 --whisper-model medium

# Specify correct language
memvid put memory.mv2 --input audio.mp3 --language es

# Check audio quality - Whisper works best with clear audio

# Check frame exists
memvid view memory.mv2 --frame-id frame_abc

# Try preview mode first
memvid view memory.mv2 --frame-id frame_abc --preview

# Check file format support
memvid stats memory.mv2 --json | jq '.frames[] | select(.uri | contains("video"))'

# Reduce concurrent processing
memvid put memory.mv2 --input video.mp4 --max-concurrent 1

# Use smaller model
memvid put memory.mv2 --input video.mp4 --whisper-model base

# Process in segments
memvid put memory.mv2 --input video.mp4 --segment-duration 300

import subprocess

# Ingest via CLI
subprocess.run([
    'memvid', 'put', 'memory.mv2',
    '--input', 'audio.mp3',
    '--language', 'en'
])

# Search transcriptions via SDK
from memvid import use
mem = use('basic', 'memory.mv2')
results = mem.find("meeting action items")