clarity-helper/services/voiceAuditionService.ts

import { synthesizeSpeechWithOpenRouter } from './openRouterService';
import { synthesizeSpeechWithGemini } from './geminiVoiceService';
import { getGeminiApiKey, hasGeminiApiKey, hasOpenRouterApiKey } from './apiConfig';
import { VOICE_PROFILES, type VoiceProfile } from '../constants';
import type { UserSettings } from '../types';

export interface VoicePlaybackState {
  isPlaying: boolean;
  activeVoiceId: UserSettings['voiceName'] | null;
  mode: 'gemini' | 'openrouter' | 'webspeech' | 'idle';
  error?: string;
}

export function getActiveVoiceEngine(): 'gemini' | 'openrouter' | 'webspeech' {
  if (hasGeminiApiKey()) return 'gemini';
  if (hasOpenRouterApiKey()) return 'openrouter';
  return 'webspeech';
}

export class VoiceAuditionService {
  private currentAudio: HTMLAudioElement | null = null;
  private currentAudioUrl: string | null = null;
  private activeUtterance: SpeechSynthesisUtterance | null = null;

  /**
   * Returns the VoiceProfile configuration for a given voice name.
   */
  getProfile(voiceId: UserSettings['voiceName']): VoiceProfile {
    return VOICE_PROFILES.find((p) => p.id === voiceId) || VOICE_PROFILES[0];
  }

  /**
   * Auditions/plays a voice sample:
   * 1. Google Gemini native voice (gemini-3.8-flash-tts) if GEMINI_API_KEY is available.
   * 2. OpenRouter TTS if OPENROUTER_API_KEY is available.
   * 3. Browser Web Speech Synthesis fallback.
   */
  async playPreview(
    voiceId: UserSettings['voiceName'],
    customText?: string,
    apiKey?: string,
    onEnded?: () => void,
    geminiApiKey?: string
  ): Promise<void> {
    this.stop();

    const profile = this.getProfile(voiceId);
    const textToSpeak = customText?.trim() || profile.sampleText;

    // 1. Prioritize Google Gemini Native Voice (gemini-3.8-flash-tts)
    const geminiKey = getGeminiApiKey(geminiApiKey);
    if (geminiKey) {
      try {
        const arrayBuffer = await synthesizeSpeechWithGemini(
          textToSpeak,
          profile.id,
          geminiKey
        );
        const blob = new Blob([arrayBuffer], { type: 'audio/wav' });
        const url = URL.createObjectURL(blob);
        this.currentAudioUrl = url;
        const audio = new Audio(url);
        this.currentAudio = audio;

        audio.onended = () => {
          this.cleanupAudio();
          onEnded?.();
        };

        audio.onerror = () => {
          this.cleanupAudio();
          this.playWebSpeech(textToSpeak, profile, onEnded);
        };

        await audio.play();
        return;
      } catch (err) {
        console.warn('Gemini 3.8 native voice synthesis preview failed, checking OpenRouter fallback:', err);
      }
    }

    // 2. OpenRouter TTS Fallback
    if (apiKey && apiKey.trim().length > 0) {
      try {
        const arrayBuffer = await synthesizeSpeechWithOpenRouter(
          textToSpeak,
          profile.openRouterVoice,
          apiKey
        );
        const blob = new Blob([arrayBuffer], { type: 'audio/mpeg' });
        const url = URL.createObjectURL(blob);
        this.currentAudioUrl = url;
        const audio = new Audio(url);
        this.currentAudio = audio;

        audio.onended = () => {
          this.cleanupAudio();
          onEnded?.();
        };

        audio.onerror = () => {
          this.cleanupAudio();
          this.playWebSpeech(textToSpeak, profile, onEnded);
        };

        await audio.play();
        return;
      } catch (err) {
        console.warn('OpenRouter TTS preview failed, falling back to Web Speech Synthesis:', err);
      }
    }

    // 3. Web Speech API fallback with calibrated pitch/rate tuning
    this.playWebSpeech(textToSpeak, profile, onEnded);
  }

  private playWebSpeech(
    text: string,
    profile: VoiceProfile,
    onEnded?: () => void
  ): void {
    const synth = typeof window !== 'undefined' && 'speechSynthesis' in window
      ? window.speechSynthesis
      : (typeof (globalThis as any).speechSynthesis !== 'undefined' ? (globalThis as any).speechSynthesis : null);

    const Utterance = typeof window !== 'undefined' && 'SpeechSynthesisUtterance' in window
      ? window.SpeechSynthesisUtterance
      : (typeof (globalThis as any).SpeechSynthesisUtterance !== 'undefined' ? (globalThis as any).SpeechSynthesisUtterance : null);

    if (synth && Utterance) {
      synth.cancel();
      const utterance = new Utterance(text);
      utterance.pitch = profile.webSpeechTuning.pitch;
      utterance.rate = profile.webSpeechTuning.rate;

      utterance.onend = () => {
        this.activeUtterance = null;
        onEnded?.();
      };

      utterance.onerror = () => {
        this.activeUtterance = null;
        onEnded?.();
      };

      this.activeUtterance = utterance;
      synth.speak(utterance);
    } else {
      onEnded?.();
    }
  }

  private cleanupAudio(): void {
    if (this.currentAudioUrl) {
      URL.revokeObjectURL(this.currentAudioUrl);
      this.currentAudioUrl = null;
    }
    this.currentAudio = null;
  }

  /**
   * Immediately stops any active audition preview audio.
   */
  stop(): void {
    if (this.currentAudio) {
      try {
        this.currentAudio.pause();
        this.currentAudio.currentTime = 0;
      } catch (e) {}
      this.cleanupAudio();
    }

    const synth = typeof window !== 'undefined' && 'speechSynthesis' in window
      ? window.speechSynthesis
      : (typeof (globalThis as any).speechSynthesis !== 'undefined' ? (globalThis as any).speechSynthesis : null);

    if (synth) {
      try {
        synth.cancel();
      } catch (e) {}
      this.activeUtterance = null;
    }
  }
}

export const defaultVoiceAudition = new VoiceAuditionService();