feat: Add category filters (한영혼합, 숫자혼합, 긴문장) to leaderboard

fix: Hide inactive models from leaderboard

feat: Keep only Typecast v3 (자인), deactivate 재선 and legacy models

chore: Trigger space restart for new Typecast models

feat: Re-enable Typecast v3.0

fix: Update Typecast default model to ssfm-v30

fix: Temporarily disable Typecast v3.0 (503 errors from HF Space)

feat: Add retry logic for Typecast API (3 retries with exponential backoff)

feat: Upgrade Typecast to v3.0 API (ssfm-v30), add Jaesun & Jain voices, deactivate legacy GeumHee

fix: Gemini TTS requires service account JSON (API Key not supported), disable until JSON provided

fix: Use REST API v1beta1 for Gemini TTS, disable google-wavenet/neural2

fix: Use GEMINI_TTS_API_KEY -> GOOGLE_API_KEY for Gemini TTS (client lib reads this env var)

fix: Require service account for Gemini TTS and disable legacy Typecast model

fix: Use REST API v1beta1 for Gemini TTS (supports API Key)

fix: Gemini TTS requires service account JSON (API key not supported by client lib), disable until JSON provided

fix: Use GOOGLE_API_KEY env var for Gemini TTS (simpler than service account)

feat: Enable Gemini TTS with service account JSON authentication

fix: Add ffmpeg to Docker, disable Gemini TTS (requires OAuth2), keep REST API code for future

feat: Add Gemini TTS (Aoede voice) - Google Cloud Text-to-Speech

feat: Change Typecast voice from JaeYi to GeumHee

feat: Add Typecast TTS (JaeYi voice) - https://typecast.ai/

feat: Remove login requirement - allow anonymous TTS generation and voting

delete hf login

feat: Replace avg votes per user with total evaluation time

feat: Replace Top Voters with Statistics tab - Show total votes, avg votes per user, total characters evaluated, active models - Hide total voters count temporarily

stats (add chars)

stats

합성 to 생성

change license

delete auth

change humelo voice

change humelo voice

change humelo voice

style: improve overall arena UI design

fix: unify random button icon - use shuffle icon instead of dice emoji

fix: simplify keyboard hints - explain random button more clearly

chore: update ko_prompts.json

fix: remove ConsumedSentence logic - allow same sentence to be used multiple times

chore: remove model list section from About page

feat: add Humelo DIVE TTS (시아 voice)

feat: remove Discord link, add 16kHz audio resampling for fair comparison

feat: use HuggingFace persistent storage (/data) for database persistence

feat: Add CLOVA TTS, update OpenAI to gpt-4o-mini-tts, re-enable Supertone

Allow all votes to count for public leaderboard

Remove conversational tab from leaderboard, lower vote threshold to 0

Temporarily disable Supertone (no credits)

Fix Supertone API URL: api.supertone.ai -> supertoneapi.com

Add Supertone TTS support

Trigger rebuild

Restore Dockerfile and push updates