Preview / roadmap

Voice speaking lab

Roadmap for German speaking and shadowing practice in Podtext: conversation loops, recording, and transcript-aware drills.

• Server-side TTS already exists for episode tooling — see lib/google-ai/gemini-tts.ts.
• Alignment / ASR uses WhisperX in the generation pipeline — see lib/episode-generation/sync-align-whisperx.ts.
• TODO: feature flag NEXT_PUBLIC_FEATURE_VOICE_SPEAKING, browser capture + consent UX, and a small API route for optional scoring.

Browse episodes for listen-and-repeat with synced transcripts today.