Voice clone: read 10 sentences -> average ECAPA over all clips for a stabler centroid

Voice cloning: extract ECAPA speaker centroid from upload (no transcript); add speechbrain

Fix voice cloning: use prompt_wav+prompt_text (reference_wav_path produced gibberish); remove debug

TEMP: add /tts_debug endpoint to diagnose voice-clone content failure

Long-text streaming: stream until GPU time budget (~100s) instead of fixed 12-sentence cap

Streaming tab: sentence-by-sentence streaming for long text (synth & play per sentence)

Streaming tab: collect full audio then play smoothly (ZeroGPU is sub-realtime)

Recreate Space (zero-a10g) after region corruption; streaming included

initial commit