Architecture¶

┌─────────────┐    ┌─────────────┐    ┌─────────────┐    ┌─────────────┐
│   Parser    │───▶│     TTS     │───▶│  Recorder   │───▶│  Combiner   │
│             │    │             │    │             │    │             │
│ Marp → HTML │    │ Text → MP3  │    │ HTML → MP4  │    │ Parts → MP4 │
└─────────────┘    └─────────────┘    └─────────────┘    └─────────────┘

vac/
├── cmd/vac/     # CLI entry point
│   └── main.go
├── pkg/
│   ├── orchestrator/   # Pipeline coordination
│   │   └── orchestrator.go
│   ├── parser/         # Marp markdown parsing
│   │   ├── marp_parser.go
│   │   └── marp_parser_test.go
│   ├── tts/            # Text-to-speech generation
│   │   └── elevenlabs.go
│   ├── video/          # Video recording and combining
│   │   ├── recorder.go
│   │   ├── combiner.go
│   │   └── combiner_test.go
│   └── transcript/     # Multi-language transcript types
│       ├── transcript.go
│       └── transcript.schema.json
└── examples/           # Example presentations
    └── intro/

type Orchestrator struct {
    config    Config
    parser    *parser.MarpParser
    tts       *tts.ElevenLabsClient
    recorder  *video.Recorder
}

func (o *Orchestrator) Run(ctx context.Context) error {
    // 1. Parse Marp markdown
    // 2. Generate TTS audio for each slide
    // 3. Record screen for each slide
    // 4. Combine into final video
}

type Slide struct {
    Index   int
    Content string
    Notes   string  // Speaker notes / voiceover text
}

func (p *MarpParser) Parse(input string) ([]Slide, error)

type ElevenLabsClient struct {
    client  *elevenlabs.Client
    voiceID string
}

func (c *ElevenLabsClient) Synthesize(ctx context.Context, text string) ([]byte, error)

type Recorder struct {
    config RecorderConfig
}

func (r *Recorder) RecordSlide(ctx context.Context, htmlPath string, duration time.Duration) (string, error)

func CombineVideos(ctx context.Context, inputPaths []string, outputPath string) error
func CombineVideosWithTransitions(ctx context.Context, inputPaths []string, outputPath string, transition float64) error

slides.md
    │
    ▼
┌─────────────────────────────────┐
│ Parser.Parse()                  │
│ Extract slides + inline notes   │
└─────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────┐
│ TTS.Synthesize() × N slides     │
│ Generate audio/slide_N.mp3      │
└─────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────┐
│ Recorder.RecordSlide() × N      │
│ Generate video/slide_N.mp4      │
└─────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────┐
│ Combiner.CombineVideos()        │
│ Generate output.mp4             │
└─────────────────────────────────┘

slides.md + transcript.json
    │
    ▼
┌─────────────────────────────────┐
│ Load transcript for locale      │
│ Override voice settings         │
└─────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────┐
│ TTS.Synthesize() with segments  │
│ Apply pauses, emphasis          │
└─────────────────────────────────┘
    │
    ▼
[Same recording/combining flow]

type AvatarConfig struct {
    Provider  string `json:"provider"`  // heygen, synthesia, d-id
    AvatarID  string `json:"avatarId"`
    Position  string `json:"position"`
    Size      string `json:"size"`
}

// Current: ElevenLabs
tts := elevenlabs.NewClient(apiKey)

// Future: Deepgram, OpenAI, etc.
tts := omnivoice.NewClient("deepgram", apiKey)