secondvoice/src/ui/TranslationUI.h
StillHammer 21bcc9ed71 feat: Add transcript export and debug planning docs
- Add CLAUDE.md with project documentation for AI assistance
- Add PLAN_DEBUG.md with debugging hypotheses and logging plan
- Update Pipeline and TranslationUI with transcript export functionality

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 19:59:29 +08:00

95 lines
2.9 KiB
C++

#pragma once
#include <string>
#include <vector>
#define GLFW_INCLUDE_NONE // Don't include OpenGL headers (GLAD provides them)
#include <GLFW/glfw3.h>
namespace secondvoice {
struct TranslationMessage {
std::string chinese;
std::string french;
};
class TranslationUI {
public:
TranslationUI(int width, int height);
~TranslationUI();
bool initialize();
void makeContextCurrent(); // Make OpenGL context current in calling thread
void render();
bool shouldClose() const;
void addTranslation(const std::string& chinese, const std::string& french);
void setAccumulatedText(const std::string& chinese, const std::string& french);
bool isStopRequested() const { return stop_requested_; }
void resetStopRequest() { stop_requested_ = false; }
bool isClearRequested() const { return clear_requested_; }
void resetClearRequest() { clear_requested_ = false; }
// Export transcript to file
bool exportTranscript(const std::string& filename = "") const;
bool isExportRequested() const { return export_requested_; }
void resetExportRequest() { export_requested_ = false; }
void setRecordingDuration(int seconds) { recording_duration_ = seconds; }
void setProcessingStatus(const std::string& status) { processing_status_ = status; }
// Audio level monitoring
void setCurrentRMS(float rms) { current_rms_ = rms; }
void setCurrentPeak(float peak) { current_peak_ = peak; }
float getVadThreshold() const { return vad_threshold_; }
float getVadPeakThreshold() const { return vad_peak_threshold_; }
private:
void renderAccumulated();
void renderTranslations();
void renderControls();
void renderStatus();
void renderAudioPanel();
int width_;
int height_;
GLFWwindow* window_ = nullptr;
std::vector<TranslationMessage> messages_;
std::string accumulated_chinese_;
std::string accumulated_french_;
bool stop_requested_ = false;
bool clear_requested_ = false;
bool export_requested_ = false;
bool auto_scroll_ = true;
int recording_duration_ = 0;
std::string processing_status_;
// Audio monitoring
float current_rms_ = 0.0f;
float current_peak_ = 0.0f;
float vad_threshold_ = 0.02f; // 2x higher to avoid false triggers
float vad_peak_threshold_ = 0.08f; // 2x higher
// Cost tracking
float total_audio_seconds_ = 0.0f;
int whisper_calls_ = 0;
int claude_calls_ = 0;
public:
void addAudioCost(float seconds) {
total_audio_seconds_ += seconds;
whisper_calls_++;
}
void addClaudeCost() { claude_calls_++; }
float getTotalAudioSeconds() const { return total_audio_seconds_; }
float getEstimatedCost() const {
// gpt-4o-mini-transcribe: $0.006/min = $0.0001/sec
// Haiku: ~$0.001 per short translation
return (total_audio_seconds_ * 0.0001f) + (claude_calls_ * 0.001f);
}
};
} // namespace secondvoice