karaoke-gen 0.75.53__py3-none-any.whl → 0.81.1__py3-none-any.whl

{karaoke_gen-0.75.53.dist-info → karaoke_gen-0.81.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: karaoke-gen
-Version: 0.75.53
+Version: 0.81.1
 Summary: Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens.
 License: MIT
 License-File: LICENSE
@@ -13,12 +13,14 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Provides-Extra: local-whisper
 Requires-Dist: argparse (>=1.4.0)
 Requires-Dist: attrs (>=24.2.0)
 Requires-Dist: audio-separator[cpu] (>=0.34.0)
 Requires-Dist: beautifulsoup4 (>=4)
 Requires-Dist: cattrs (>=24.1.2)
 Requires-Dist: dropbox (>=12)
+Requires-Dist: email-validator (>=2.0.0)
 Requires-Dist: fastapi (>=0.104.0)
 Requires-Dist: fetch-lyrics-from-genius (>=0.1)
 Requires-Dist: ffmpeg-python (>=0.2.0,<0.3.0)
@@ -40,6 +42,7 @@ Requires-Dist: kbputils (>=0.0.16,<0.0.17)
 Requires-Dist: langchain (>=0.3.0)
 Requires-Dist: langchain-anthropic (>=0.2.0)
 Requires-Dist: langchain-core (>=0.3.0)
+Requires-Dist: langchain-google-vertexai (>=2.0.0)
 Requires-Dist: langchain-ollama (>=0.2.0)
 Requires-Dist: langchain-openai (>=0.2.0)
 Requires-Dist: langfuse (>=3.0.0)
@@ -74,10 +77,12 @@ Requires-Dist: python-levenshtein (>=0.26)
 Requires-Dist: python-multipart (>=0.0.20,<0.0.21)
 Requires-Dist: python-slugify (>=8)
 Requires-Dist: requests (>=2)
+Requires-Dist: sendgrid (>=6.10.0)
 Requires-Dist: shortuuid (>=1.0.13)
 Requires-Dist: spacy (>=3.8.7)
 Requires-Dist: spacy-syllables (>=3)
 Requires-Dist: srsly (>=2.5.1)
+Requires-Dist: stripe (>=7.0.0)
 Requires-Dist: syllables (>=1)
 Requires-Dist: syrics (>=0)
 Requires-Dist: thefuzz (>=0.22)
@@ -86,6 +91,7 @@ Requires-Dist: torch (>=2.7)
 Requires-Dist: tqdm (>=4.67)
 Requires-Dist: transformers (>=4.47)
 Requires-Dist: uvicorn[standard] (>=0.24.0)
+Requires-Dist: whisper-timestamped (>=1.15.0) ; extra == "local-whisper"
 Requires-Dist: yt-dlp (>=2024.0.0)
 Project-URL: Documentation, https://github.com/nomadkaraoke/karaoke-gen/blob/main/README.md
 Project-URL: Homepage, https://github.com/nomadkaraoke/karaoke-gen
@@ -165,8 +171,40 @@ export AUDIOSHAKE_API_TOKEN="your_audioshake_token"
 
 Get an API key at [https://www.audioshake.ai/](https://www.audioshake.ai/) - business only, at time of writing this.
 
-#### Option 2: Whisper via RunPod
-Open-source alternative using OpenAI's Whisper model on RunPod infrastructure.
+#### Option 2: Local Whisper (No Cloud Required)
+Run Whisper directly on your local machine using whisper-timestamped. Works on CPU, NVIDIA GPU (CUDA), or Apple Silicon.
+
+```bash
+# Install with local Whisper support
+pip install "karaoke-gen[local-whisper]"
+
+# Optional: Configure model size (tiny, base, small, medium, large)
+export WHISPER_MODEL_SIZE="medium"
+
+# Optional: Force specific device (cpu, cuda, mps)
+export WHISPER_DEVICE="cpu"
+```
+
+**Model Size Guide:**
+| Model | VRAM | Speed | Quality |
+|-------|------|-------|---------|
+| tiny | ~1GB | Fast | Lower |
+| base | ~1GB | Fast | Basic |
+| small | ~2GB | Medium | Good |
+| medium | ~5GB | Slower | Better |
+| large | ~10GB | Slowest | Best |
+
+**CPU-Only Installation** (no GPU required):
+```bash
+# Pre-install CPU-only PyTorch first
+pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
+pip install "karaoke-gen[local-whisper]"
+```
+
+Local Whisper runs automatically as a fallback when no cloud transcription services are configured.
+
+#### Option 3: Whisper via RunPod
+Cloud-based alternative using OpenAI's Whisper model on RunPod infrastructure.
 
 ```bash
 export RUNPOD_API_KEY="your_runpod_key"
@@ -308,7 +346,7 @@ karaoke-gen-remote \
 |----------|-------------|---------|
 | `KARAOKE_GEN_URL` | Backend service URL | Required |
 | `KARAOKE_GEN_AUTH_TOKEN` | Admin auth token (for protected endpoints) | Optional |
-| `REVIEW_UI_URL` | Lyrics review UI URL | `https://lyrics.nomadkaraoke.com` |
+| `REVIEW_UI_URL` | Lyrics review UI URL | `https://gen.nomadkaraoke.com/lyrics/` |
 | `POLL_INTERVAL` | Seconds between status polls | `5` |
 
 **Note:** The `REVIEW_UI_URL` defaults to the hosted lyrics review UI. For local development, set it to `http://localhost:5173` if you're running the frontend dev server.
@@ -668,6 +706,44 @@ If the output video has quality problems:
 - Check available codecs: `ffmpeg -codecs`
 - For 4K output, ensure sufficient disk space (10GB+ per track)
 
+### Local Whisper Issues
+
+#### GPU Out of Memory
+If you get CUDA out of memory errors:
+```bash
+# Use a smaller model
+export WHISPER_MODEL_SIZE="small"  # or "tiny"
+
+# Or force CPU mode
+export WHISPER_DEVICE="cpu"
+```
+
+#### Slow Transcription on CPU
+CPU transcription is significantly slower than GPU. For faster processing:
+- Use a smaller model (`tiny` or `base`)
+- Consider using cloud transcription (AudioShake or RunPod)
+- On Apple Silicon, the `small` model offers good speed/quality balance
+
+#### Model Download Issues
+Whisper models are downloaded on first use (~1-3GB depending on size). If downloads fail:
+- Check your internet connection
+- Set a custom cache directory: `export WHISPER_CACHE_DIR="/path/with/space"`
+- Models are cached in `~/.cache/whisper/` by default
+
+#### whisper-timestamped Not Found
+If you get "whisper-timestamped is not installed":
+```bash
+pip install "karaoke-gen[local-whisper]"
+# Or install directly:
+pip install whisper-timestamped
+```
+
+#### Disabling Local Whisper
+If you want to disable local Whisper (e.g., to force cloud transcription):
+```bash
+export ENABLE_LOCAL_WHISPER="false"
+```
+
 ---
 
 ## 🧪 Development

{karaoke_gen-0.75.53.dist-info → karaoke_gen-0.81.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
 karaoke_gen/__init__.py,sha256=wHpDbURJxmJAMNZ0uQjISv5MIT7KD9RWYi15xlYgEhU,1351
-karaoke_gen/audio_fetcher.py,sha256=A1c7HxUbV4inhGuj9SySr3zkOSGKfAFovXu2TKzodSA,63811
+karaoke_gen/audio_fetcher.py,sha256=EuMSO_wG0z0ldfQQ_xGC8kdoUCDB1Rr2_IuWIZ218lA,71380
 karaoke_gen/audio_processor.py,sha256=YCMsxh-OSzC6h1Oqht8gh48j4KaRDuRIMUUsNNQxJeY,39913
 karaoke_gen/config.py,sha256=LBZKpvwSgta8YoVX2GFFW-4CP22AyRtqsBn-KCeh8eg,2499
 karaoke_gen/file_handler.py,sha256=jnPc4kFtG-PX-IVPHYWa7maXd4lNmbkKd1HogDNzgN8,16674
@@ -8,12 +8,12 @@ karaoke_gen/instrumental_review/analyzer.py,sha256=Heg8TbrwM4g5IV7bavmO6EfVD4M0U
 karaoke_gen/instrumental_review/editor.py,sha256=_DGTjKMk5WhoGtLGtTvHzU522LJyQQ_DSY1r8fULuiA,11568
 karaoke_gen/instrumental_review/models.py,sha256=cUSb_JheJK0cGdKx9f59-9sRvRrhrgdTdKBzQN3lHto,5226
 karaoke_gen/instrumental_review/server.py,sha256=Ick90X77t2EeMRwtx2U08sSybadQyWH7G0tDG-4JqP4,19377
-karaoke_gen/instrumental_review/static/index.html,sha256=EjMFxCQJOUSrsgwIXAW3R4bN6hYxDLmL4MHzoXxI4f0,59362
+karaoke_gen/instrumental_review/static/index.html,sha256=1lzo_W5B4HxNStWPiVaP4I6ctqDkXAABJkQmojvBDqc,63235
 karaoke_gen/instrumental_review/waveform.py,sha256=Q6LBPZrJAD6mzZ7TmRf3Tf4gwYhUYTHumJKytLs3hSg,12940
 karaoke_gen/karaoke_finalise/__init__.py,sha256=HqZ7TIhgt_tYZ-nb_NNCaejWAcF_aK-7wJY5TaW_keM,46
 karaoke_gen/karaoke_finalise/karaoke_finalise.py,sha256=Wn1KcdRyINT63UxKUPT9uB-bsrFVih0Im_cjXtequS0,93534
-karaoke_gen/karaoke_gen.py,sha256=tfoywlSEI9qOi1krHTBafumXl3bcWxn6w0AN2vQ1nHs,57048
-karaoke_gen/lyrics_processor.py,sha256=JrbTLmMR_jvcpuxsPihLXlCBKkFNKqYHvraw3_3KCPI,23263
+karaoke_gen/karaoke_gen.py,sha256=84n2SE0MixJr01_btLmm5cVdf35hJvp7W638b8TKR-Q,65734
+karaoke_gen/lyrics_processor.py,sha256=9BtL2uJa4Ekrodj2w_SXSeOraVKCB2kzYuHcGHTFpo8,23979
 karaoke_gen/metadata.py,sha256=SZW6TuUpkGGU98gRdjPfrR8F4vWXjnfCSGry2XD5_A4,6689
 karaoke_gen/pipeline/__init__.py,sha256=-MZnba4qobr1qGDamG9CieLl2pWCZMEB5_Yur62RKeM,2106
 karaoke_gen/pipeline/base.py,sha256=yg4LIm7Mc9ER0zCmZcUv4huEkotSSXK_0OAFio-TSNI,6235
@@ -33,19 +33,19 @@ karaoke_gen/resources/Oswald-Bold.ttf,sha256=S_2mLpNkBsDTe8FQRzrj1Qr-wloGETMJgoA
 karaoke_gen/resources/Oswald-SemiBold.ttf,sha256=G-vSJeeyEVft7D4s7FZQtGfXAViWPjzGCImV2a4u9d8,87608
 karaoke_gen/resources/Zurich_Cn_BT_Bold.ttf,sha256=WNG5LOQ-uGUF_WWT5aQHzVbyWvQqGO5sZ4E-nRmvPuI,37780
 karaoke_gen/style_loader.py,sha256=13010BVxwVgamRn8K8Z9fNgLBdPs9LFmWMRMLyBdits,17908
-karaoke_gen/utils/__init__.py,sha256=FpOHyeBRB06f3zMoLBUJHTDZACrabg-DoyBTxNKYyNY,722
+karaoke_gen/utils/__init__.py,sha256=zAb4sG4GMkBlkD2G1EDu-GsMbjcjFT127lFBwh0xVPI,1875
 karaoke_gen/utils/bulk_cli.py,sha256=s2SXTnnQf7TM8Fk8yz9Cfd3Xl08uHBnve_rTkf4wE5g,19337
-karaoke_gen/utils/cli_args.py,sha256=Td8fE1FisY1fcQuOoKlAQ6B3NF4bxGvSPDaQlpfY3T0,18172
-karaoke_gen/utils/gen_cli.py,sha256=ahoVp_n298O8yUmFOBDsm4mLXgTuEb80mBnz4_mo4SM,44137
-karaoke_gen/utils/remote_cli.py,sha256=l1iHUz_hrsbAfTvGDhA4gzr2g1CFBFc9np0nQ1jk1tQ,144629
+karaoke_gen/utils/cli_args.py,sha256=4m2EOaxg-bYzXmlSOkpQUoVSi2Q9Xr3VtBZA7z3quBk,18515
+karaoke_gen/utils/gen_cli.py,sha256=5ydiudcIOmNvA-YHe7x6QZepoQGg1dtW4bOkNOBhXhY,44142
+karaoke_gen/utils/remote_cli.py,sha256=sWlbu29fQwoqNtIYUeC9nipux36sFJAUe-aMbGCGv_c,145647
 karaoke_gen/video_background_processor.py,sha256=p3sryMxmkori4Uy2MYgmlk5_QQ7Uh9IoVJLAdkdLIUI,15124
 karaoke_gen/video_generator.py,sha256=B7BQBrjkyvk3L3sctnPXnvr1rzkw0NYx5UCAl0ZiVx0,18464
 lyrics_transcriber/__init__.py,sha256=g9ZbJg9U1qo7XzrC25J3bTKcNzzwUJWDVdi_7-hjcM4,412
 lyrics_transcriber/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/cli/cli_main.py,sha256=F72ENLTj934bXjHAUbRm0toCK73qnuJhwEm9agBVKHQ,11596
 lyrics_transcriber/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lyrics_transcriber/core/config.py,sha256=AM6RZKll8tzdZtMLgvHRQb1SxiXVPek0q4vmSWVUvEo,1368
-lyrics_transcriber/core/controller.py,sha256=laeUakqT-0CoIyoBWYvv7kWxX-_wefWRwg2xrz84gRg,29432
+lyrics_transcriber/core/config.py,sha256=_X_d1wSYTJjSquqbODYCwPdOYpnSR9KERwvr_jkdYls,2056
+lyrics_transcriber/core/controller.py,sha256=dUJvnehr9_Mv3Syj_TWZQsQVsDD1w8AdF5_1xISA2cw,31661
 lyrics_transcriber/correction/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/correction/agentic/__init__.py,sha256=p7PHiebuvRs8RDlPDs-9gLZKzXG5KfWg3fFCdDhY6pE,222
 lyrics_transcriber/correction/agentic/adapter.py,sha256=Z0JBTAA7xlSdctCHqO9nBMl78C4XmqsLKKtS6BvNZNI,2912
@@ -83,15 +83,15 @@ lyrics_transcriber/correction/agentic/prompts/classifier.py,sha256=pKbL4Cyj0-c_O
 lyrics_transcriber/correction/agentic/providers/__init__.py,sha256=PS7C4sKDfa6S9lSo33GXIRamCLsv0Jn7u0GtXuhiRD4,95
 lyrics_transcriber/correction/agentic/providers/base.py,sha256=bExuntMLLInMmWWNzN81_ScWQJhNYbtlF3wZYhlX-qw,1059
 lyrics_transcriber/correction/agentic/providers/circuit_breaker.py,sha256=D3Jg4YHqvy4gzlxfkALa7PztyYQpJb8NwJAonMS0TSI,4694
-lyrics_transcriber/correction/agentic/providers/config.py,sha256=FsX1xIF1UG_Kbxp4tlEnZc68AsRTL4Q4XenP_VuRi6o,2937
+lyrics_transcriber/correction/agentic/providers/config.py,sha256=2dy9zynj8hU3LdRkb2RmKSOztsX4_Ay23EU-RfUGCrM,3206
 lyrics_transcriber/correction/agentic/providers/constants.py,sha256=aDIEsDvNQLEGlGk8klAaRxJmdldGBDFqwYLuCmlYoNM,692
 lyrics_transcriber/correction/agentic/providers/health.py,sha256=F8pHY5BQYvylGRDGXUHplcAJooAyiqVLRhBl4kHC1H8,710
 lyrics_transcriber/correction/agentic/providers/langchain_bridge.py,sha256=hderNRLrSZn49LrGBrgdCvBP5E7tPAugjaw7TFbb0JY,7957
-lyrics_transcriber/correction/agentic/providers/model_factory.py,sha256=ITPc7BLIhtHKzobERl0P7YsmunOquqbaJ_M5tinztx4,7667
+lyrics_transcriber/correction/agentic/providers/model_factory.py,sha256=iKbpMEeTyhPN8n9abVf645TfovnFEz3ia1g6XLHqp4s,8613
 lyrics_transcriber/correction/agentic/providers/response_cache.py,sha256=Byr7fQJsgUMFlsvHeVCxTiFjjnbsg3KIlEmEEtAo-Gw,7047
 lyrics_transcriber/correction/agentic/providers/response_parser.py,sha256=a8pdUYKBS5X72gck3u1ndFYB__UN0UijAdxNhbHp8ZQ,3809
 lyrics_transcriber/correction/agentic/providers/retry_executor.py,sha256=hX21Zwy2cSECAw7k13ndEinWRqwjo4xYoSCQ2B2CUf0,3912
-lyrics_transcriber/correction/agentic/router.py,sha256=pk4xeS-BZLGJMdFj7Q7MjNaqYJF_glI590z9Alg15co,1229
+lyrics_transcriber/correction/agentic/router.py,sha256=_JtnXgcIdui6qeN9x0EawThDGZavAwfpbtEJAYVlQTY,1334
 lyrics_transcriber/correction/agentic/workflows/__init__.py,sha256=OsBExAbIIKxJgX6FKXFOgcUjIG9AWJQV_fESZVdO8mo,77
 lyrics_transcriber/correction/agentic/workflows/consensus_workflow.py,sha256=gMuLTUxkgYaciMsI4yrZSC3wi--7V_PgaDNE-Vd6FE8,575
 lyrics_transcriber/correction/agentic/workflows/correction_graph.py,sha256=kgZKnz0h9cG1EfhW7BSSl-kSpQtJrRM_S86kAniXfE4,1815
@@ -117,15 +117,19 @@ lyrics_transcriber/correction/handlers/word_operations.py,sha256=410xhyO9tiqezV5
 lyrics_transcriber/correction/operations.py,sha256=k5N8w_8BeR7CXiclaJ3zuu_g2KLoWSnnuD4OAmY3kJs,14010
 lyrics_transcriber/correction/phrase_analyzer.py,sha256=dtO_2LjxnPdHJM7De40mYIdHCkozwhizVVQp5XGO7x0,16962
 lyrics_transcriber/correction/text_utils.py,sha256=7QHK6-PY7Rx1G1E31sWiLBw00mHorRDo-M44KMHFaZs,833
-lyrics_transcriber/frontend/.gitignore,sha256=lgGIPiVpFVUNSZl9oNQLelLOWUzpF7sikLW8xmsrrqI,248
+lyrics_transcriber/frontend/.gitignore,sha256=cR2ofyyWArkna_jByfaWi8gTeMhsKTSoK128PmIw218,262
 lyrics_transcriber/frontend/.yarn/releases/yarn-4.7.0.cjs,sha256=KTYy2KCV2OpHhussV5jIPDdUSr7RftMRhqPsRUmgfAY,2765465
 lyrics_transcriber/frontend/.yarnrc.yml,sha256=0hZQ1OTcPqTUNBqQeme4VFkIzrsabHNzLtc_M-wSgIM,66
 lyrics_transcriber/frontend/README.md,sha256=-D6CAfKTT7Y0V3EjlZ2fMy7fyctFQ4x2TJ9vx6xtccM,1607
 lyrics_transcriber/frontend/REPLACE_ALL_FUNCTIONALITY.md,sha256=iRZbicW5satHel9gbG-uLyZ7oq3xdp87KQlJEL1ZhK8,8384
 lyrics_transcriber/frontend/__init__.py,sha256=nW8acRSWTjXoRwGqcTU4w-__X7tMAE0iXL0uihBN3CU,836
+lyrics_transcriber/frontend/e2e/agentic-corrections.spec.ts,sha256=yNynyV8dUfwRJ1a0Cdr6o2SZEMFiuGAQG1ZM0Ro8q9o,7359
+lyrics_transcriber/frontend/e2e/fixtures/agentic-correction-data.json,sha256=_h-nI76gPXuqWErpTBrZaTgcc8LNLi6j81t3Wtt--ac,8184
 lyrics_transcriber/frontend/eslint.config.js,sha256=3ADH23ANA4NNBKFy6nCVk65e8bx1DrVd_FIaYNnhuqA,734
-lyrics_transcriber/frontend/index.html,sha256=u1m7042a1kLWZVIElYQ9y-lzfIAdYJGtQE-i4Zjc3xY,806
-lyrics_transcriber/frontend/package.json,sha256=5krvXBc9deVYXREN9Pxw5N6ohiAsSCnPXnXlcb6p-U0,1182
+lyrics_transcriber/frontend/index.html,sha256=hcVQvxU1yITMrMS4vVLwn4YwvnlXsfl4XY9UNtXvWAw,1135
+lyrics_transcriber/frontend/package-lock.json,sha256=gQekpsz4CAKMJ8Fi331Q3Pv5yqhZlQ-nbGoDNnF35WE,159262
+lyrics_transcriber/frontend/package.json,sha256=qujjeqPUSJizfHxK_2egicJYea8fziJO4O6u2A6N9Xw,1395
+lyrics_transcriber/frontend/playwright.config.ts,sha256=l5aoc_rEbrYxIipTAVbpRER0FL5bAevYtRTT-chGUqA,1523
 lyrics_transcriber/frontend/public/android-chrome-192x192.png,sha256=lg-6aPF5mGLiuG7LyftZk_0RI41srmpA8wj-NkaaQms,17632
 lyrics_transcriber/frontend/public/android-chrome-512x512.png,sha256=x-zuKT3NYsTqAWzhKRTZeD4-0uYoUjqMPZpKTChqNJ8,123447
 lyrics_transcriber/frontend/public/apple-touch-icon.png,sha256=6y5vGra54w5oc8VP6sn2JjoQtN9hWTKn0YPhmdlmfU0,16188
@@ -133,27 +137,29 @@ lyrics_transcriber/frontend/public/favicon-16x16.png,sha256=2wy_7ZmVS4d7umByJVHQ
 lyrics_transcriber/frontend/public/favicon-32x32.png,sha256=6TyrRMIw6G8dpG4_QWVTY8DMxo0bIGzc_9aOJrkiJKM,1297
 lyrics_transcriber/frontend/public/favicon.ico,sha256=ZK7QvdBuZp0QxPkluCW4IKxfleFmFLp1KkG_d5xmx7E,15406
 lyrics_transcriber/frontend/public/nomad-karaoke-logo.png,sha256=jTTBFXV6hGJGolZYQ-dIjgQQbMsehk5XGtsllhLrdzg,212641
-lyrics_transcriber/frontend/src/App.tsx,sha256=XI93-pX2p76ID45XUQTitDclUZHZ1kxhZZB2VriMV8k,6747
+lyrics_transcriber/frontend/public/nomad-karaoke-logo.svg,sha256=0LOH346_a-1JeYquMWd1v2A3XMN8zLDBeujfWAOeNYk,9185
+lyrics_transcriber/frontend/src/App.tsx,sha256=STVmqN3xtXambV_5X4M0MNuwYjARHBQfn1cuCqxNGkw,7979
 lyrics_transcriber/frontend/src/api.ts,sha256=GcjbOrlU7EdUpZ7MUPFqE1rtH-ckdw8wHtgyQxWateY,8648
-lyrics_transcriber/frontend/src/components/AIFeedbackModal.tsx,sha256=N-M8LNKE3nCjrSkWTf8ObWSdBqD0Cv3Xiz_wVv9OtFo,3133
+lyrics_transcriber/frontend/src/components/AIFeedbackModal.tsx,sha256=kDmfdTgPzqNVPMbh6ztkVod5iXE7QAfgkMMyseO07ww,5602
 lyrics_transcriber/frontend/src/components/AddLyricsModal.tsx,sha256=ubJwQewryjUrXwpBkITQNu4POhoUtDbNA93cqa-yJKY,3416
 lyrics_transcriber/frontend/src/components/AgenticCorrectionMetrics.tsx,sha256=Yg6FG0LtrneRfAYeBu3crt_RdN-_o7FojtYhDMDKi0o,8595
+lyrics_transcriber/frontend/src/components/AppHeader.tsx,sha256=5KUVADDv9cAs2WNX9M31utQIYHKMi81unzrCW3j1fl0,2396
 lyrics_transcriber/frontend/src/components/AudioPlayer.tsx,sha256=XOCz0VtGiAIBs1qnCwrAixwfgHbTSGpjEb1jQg8wqzc,5441
-lyrics_transcriber/frontend/src/components/CorrectedWordWithActions.tsx,sha256=4FK9vqjTMxnwlqxZ2E349H1S-X6SqLAYfj5U5AyuGtI,4764
+lyrics_transcriber/frontend/src/components/CorrectedWordWithActions.tsx,sha256=Z5i0MMaFC1dbafUsZVsNEMkdoqBLjkA6yCWtjoMmqi8,5207
 lyrics_transcriber/frontend/src/components/CorrectionAnnotationModal.tsx,sha256=XtF5XNLL2ztm714tXql7rKi2BX4k_bsizpZ_ZCvpu8s,13368
 lyrics_transcriber/frontend/src/components/CorrectionDetailCard.tsx,sha256=Hp-i1iSB3pzrpPH2wIREtEHHaReimBaYi8vcSUUArlg,9512
 lyrics_transcriber/frontend/src/components/CorrectionMetrics.tsx,sha256=CoTZS9Z3pf4lfPrzpQ2hZvLqFvt-IarSGBSCxFxD-y4,6274
-lyrics_transcriber/frontend/src/components/DurationTimelineView.tsx,sha256=eylYwAKHTK_5n54njn9bfMkXTGvrqsXlu9tETqAlMtA,9815
+lyrics_transcriber/frontend/src/components/DurationTimelineView.tsx,sha256=d950EHJ52ODkygUkdlO4QNta5Ru8h7DRZIqR8IjOlvQ,10121
 lyrics_transcriber/frontend/src/components/EditActionBar.tsx,sha256=nLRVA3m3bQFqLtqlYasn7WeZNXvPvpG0sXuIv5QXvDc,2174
-lyrics_transcriber/frontend/src/components/EditModal.tsx,sha256=sv-NCKMvso3UF1_fJKbzt_wAcDLAyLqRq_D24uQRrRw,24649
+lyrics_transcriber/frontend/src/components/EditModal.tsx,sha256=4smUvxF-45k-SAGXwkoBJmV37-nWWkE7HsR9w1OS6x8,24687
 lyrics_transcriber/frontend/src/components/EditTimelineSection.tsx,sha256=VQy5fpzKBG_9ZLyWHB8b8Ii61YwckCOjnYf1oezY0d4,19586
-lyrics_transcriber/frontend/src/components/EditWordList.tsx,sha256=atl-9Z-24U-KWojwo0apTy1Y9DbQGoVo2dFX4P-1Z9E,13681
+lyrics_transcriber/frontend/src/components/EditWordList.tsx,sha256=XN59JnNPYNI4KrSenW7cYC6zUIlK7GvlyRbj9eg-Eac,13716
 lyrics_transcriber/frontend/src/components/FileUpload.tsx,sha256=fwn2rMWtMLPTZLREMb3ps4prSf9nzxGwnjmeC6KYsJA,2383
 lyrics_transcriber/frontend/src/components/FindReplaceModal.tsx,sha256=U7duKns4IqNXwbWFbQfdyaswnvkSRpfsU0UG__-Serc,20192
-lyrics_transcriber/frontend/src/components/Header.tsx,sha256=KE8TirDEUgojgHjP9R4HTtCxaVr_CWumky-Es7xAGsE,18754
-lyrics_transcriber/frontend/src/components/LyricsAnalyzer.tsx,sha256=TFo2HCr6k9bENsQm-AfT797ZyFLqvKDa8g5W-pw1v24,54256
+lyrics_transcriber/frontend/src/components/Header.tsx,sha256=_lIo1ZsObF1lygXYX865Rhj053KPWvPewi7e0p11xuA,23429
+lyrics_transcriber/frontend/src/components/LyricsAnalyzer.tsx,sha256=9UZbTAXXTcYgFWwr030z-vrd8vklYrmgDCxCrPifho8,59256
 lyrics_transcriber/frontend/src/components/LyricsSynchronizer/SyncControls.tsx,sha256=j4rQjBQVbaPsp1ra_rvEoCqmX3JFJdfNnFvj3BvfsgQ,6069
-lyrics_transcriber/frontend/src/components/LyricsSynchronizer/TimelineCanvas.tsx,sha256=h-sAfDFm-DfayZbKuNJmbAqxmMr89oC26xI4WB45bxA,26896
+lyrics_transcriber/frontend/src/components/LyricsSynchronizer/TimelineCanvas.tsx,sha256=DuQBAdF8bYcAYKNEWVklXSAlEykhIDQKbELq_4SEPCg,27415
 lyrics_transcriber/frontend/src/components/LyricsSynchronizer/UpcomingWordsBar.tsx,sha256=BXkEeo5yMgHkeOCBcZKqxMb1rspjXH-X5_6X9Hl7z3E,2588
 lyrics_transcriber/frontend/src/components/LyricsSynchronizer/index.tsx,sha256=jOAmlkodaGzceQLG11ihprFMcARVbeJ_qjMcUkQj5Oo,34275
 lyrics_transcriber/frontend/src/components/MetricsDashboard.tsx,sha256=33XpyHj0siBQivE8vLgliyiwmdsAfnNQh5Py4mnhXi8,1724
@@ -161,22 +167,22 @@ lyrics_transcriber/frontend/src/components/ModeSelectionModal.tsx,sha256=eihGI49
 lyrics_transcriber/frontend/src/components/ModeSelector.tsx,sha256=HnBAK_gFgNBJLtMC_ESMVdUapDjmqmoLX8pQeyHfpOw,2651
 lyrics_transcriber/frontend/src/components/ModelSelector.tsx,sha256=lfG_B5VAzSfrU0FqJl8XptN6DVt2kSljU96HMXo8mf4,559
 lyrics_transcriber/frontend/src/components/PreviewVideoSection.tsx,sha256=59ZhG5XsxUZ_dkK8BjTQhYmYP5Wv86uRR-xtuwFRK8c,5582
-lyrics_transcriber/frontend/src/components/ReferenceView.tsx,sha256=2ugpkVtxZLS6Al-lmYbMZj7d3w9e2qNNYKJjkSxZ_X8,10494
+lyrics_transcriber/frontend/src/components/ReferenceView.tsx,sha256=_9idlSTHQ8YZqPslhpuW8R_6kAHGWPMC9GvikpwH-AY,10532
 lyrics_transcriber/frontend/src/components/ReplaceAllLyricsModal.tsx,sha256=pVlqHrSloxXZV_Ib8cbk1invF7WA3uge5b7pnFPe9Pc,12290
 lyrics_transcriber/frontend/src/components/ReviewChangesModal.tsx,sha256=VQg_gBFViAxQu9Z75o6rOsvmH5DZBjKq9FkU8aB_7mI,13790
 lyrics_transcriber/frontend/src/components/SegmentDetailsModal.tsx,sha256=6ME02FkFwCgDAxW49yW260N4vbr80eAJ332Ex811GOo,1643
 lyrics_transcriber/frontend/src/components/TimelineEditor.tsx,sha256=gJRCxdmJo80g0h5hq5AtDHK-HbOoYhMaQYvP2WgOuRI,13201
 lyrics_transcriber/frontend/src/components/TimingOffsetModal.tsx,sha256=aivGi6ehI6cDqwtoKBb6Eif8gpPqi0t3mJT8i5Feu7Q,4803
-lyrics_transcriber/frontend/src/components/TranscriptionView.tsx,sha256=LDGK-Ac4sNMoLNofAdSsZAnCOdlPk4k9Fse6ulhgjYM,11299
-lyrics_transcriber/frontend/src/components/WordDivider.tsx,sha256=tOs_4WZGlJQ1o7sZFGLhwUoyX2jSKMa6vLZqa-1vzKY,6590
-lyrics_transcriber/frontend/src/components/shared/components/HighlightedText.tsx,sha256=ZVZ61rwrKLdlmhlNuSNR7-sgdl7JdBxVTeSeKO6K-3w,16321
+lyrics_transcriber/frontend/src/components/TranscriptionView.tsx,sha256=6FqgDS6NBbdeGMANKQyF1rjxN0CZy6tYAheOq_FTYEE,11827
+lyrics_transcriber/frontend/src/components/WordDivider.tsx,sha256=ynib_j0w0q4iOYAk7D4IyZJCq71LykX7SaD9haGlZeI,6695
+lyrics_transcriber/frontend/src/components/shared/components/HighlightedText.tsx,sha256=0WFhL8BlcIrjw1BTakP-UgG0j2pripyqG5LK66a1IOE,21333
 lyrics_transcriber/frontend/src/components/shared/components/SourceSelector.tsx,sha256=FpMn-0i1NFxdIHZN0dxHkWzIIsOEi9CJc_rQMpLyxVw,2031
-lyrics_transcriber/frontend/src/components/shared/components/Word.tsx,sha256=EcLslnFE-BIOm_7FwRxKEOnIDVoWpTrDz6MQGoH_SVg,2596
-lyrics_transcriber/frontend/src/components/shared/constants.ts,sha256=25q1qjCwzV-hR72wSb_rJSe4dVuQ0l-piLMoZSpynGQ,488
+lyrics_transcriber/frontend/src/components/shared/components/Word.tsx,sha256=CXzepxI3Negx2cqdfqLNGgesNbbIcczomXed71FupNw,2676
+lyrics_transcriber/frontend/src/components/shared/constants.ts,sha256=GByG5KFLJOX0iCs80_PLXxZKQ5FBX5Qw0Mg05Xf8Faw,1142
 lyrics_transcriber/frontend/src/components/shared/hooks/useWordClick.ts,sha256=eEgBHiKIWOzFK8eBzBgcQRv7StKpaPchqh3k2kFlwgY,6253
 lyrics_transcriber/frontend/src/components/shared/styles.ts,sha256=J1jCSuRqpk1mOFYAqJudhxeozH-q1bi-dsOibLukBJU,411
 lyrics_transcriber/frontend/src/components/shared/types.js,sha256=1DqoH1vIn6o1ng-XyBS6JRVVkf8Hj7ub_UD4x8loMjA,77
-lyrics_transcriber/frontend/src/components/shared/types.ts,sha256=22gpjxcUglmykSimUu6l_6XzgIga1fX8QIM1Mr0CpiI,3973
+lyrics_transcriber/frontend/src/components/shared/types.ts,sha256=mA7YELw4x0TI3PG2-6EuB1WmGnG36h_C4iwTOvmIoaY,4249
 lyrics_transcriber/frontend/src/components/shared/utils/keyboardHandlers.ts,sha256=Yh5c_kOdOjE84FtKVB4BBC8QIgkFk5tO0ZJa9oJqqqU,5870
 lyrics_transcriber/frontend/src/components/shared/utils/localStorage.ts,sha256=jpLT65Rk_toaB-8X2lRGyYZ9EoMQDI45GviUT7N9Bp0,3240
 lyrics_transcriber/frontend/src/components/shared/utils/referenceLineCalculator.ts,sha256=TJ2oHDitFFVxm83eFEhdlwvhx--mIt3054YbET2RiXs,2575
@@ -184,8 +190,8 @@ lyrics_transcriber/frontend/src/components/shared/utils/segmentOperations.ts,sha
 lyrics_transcriber/frontend/src/components/shared/utils/timingUtils.ts,sha256=s3xdwGPg6ltZEcQ4AzgpznAR-fLhCTCYW7pfXaD60JY,4597
 lyrics_transcriber/frontend/src/components/shared/utils/wordUtils.ts,sha256=bZbsvEgY3JoI15l4SdB51tHE33OkUxDH-WSG8doLcCQ,721
 lyrics_transcriber/frontend/src/hooks/useManualSync.ts,sha256=cP19QsK-o5uz-Udq8m5d4NhMaPupHEQQz7uf0aE4Hs8,19403
-lyrics_transcriber/frontend/src/main.tsx,sha256=qNDmjgzD2Dd4d9J42o1z0JcKBElsMWHpFIgEvI8kNi8,543
-lyrics_transcriber/frontend/src/theme.ts,sha256=9F2xyLct_gJmvLEZEhrYdKIahUsBzi5kgnydSWJHphE,3864
+lyrics_transcriber/frontend/src/main.tsx,sha256=bd2cO-7CSbqQwJ-8N3p_xPJvTFmg5lcJi2I-WgkIb6k,337
+lyrics_transcriber/frontend/src/theme.ts,sha256=bVq-h3lYZhqHbM9yE0Le6DmpJS9n_u76xe-bQ_SjGE8,12498
 lyrics_transcriber/frontend/src/types/global.d.ts,sha256=NvltPF-n4_1oRLfihD3oHXbdT7txMC8B6fhCgvNY-jk,191
 lyrics_transcriber/frontend/src/types.js,sha256=1DqoH1vIn6o1ng-XyBS6JRVVkf8Hj7ub_UD4x8loMjA,77
 lyrics_transcriber/frontend/src/types.ts,sha256=gQBu13DDbSBUtbI-TwzAlmlIYfOehXar4WuvZ9GkziE,4880
@@ -198,7 +204,7 @@ lyrics_transcriber/frontend/tsconfig.tsbuildinfo,sha256=TGnTUZG3ScMXJTHpm1GmyxtE
 lyrics_transcriber/frontend/update_version.js,sha256=PxkqCnsucXnXiIqutsanVcx00Gq4k7pgCYj_uXCa4qw,411
 lyrics_transcriber/frontend/vite.config.d.ts,sha256=S5bdGf0pSdKM6A6RNBKwAm3EIeW_bDHYfHtesRtXU7Q,76
 lyrics_transcriber/frontend/vite.config.js,sha256=P4GuPgRZzwEWPQZpyujUe7eA3mjPoFAe2CgE5sQAXg8,232
-lyrics_transcriber/frontend/vite.config.ts,sha256=8FdW0dN8zDFqfhQSxX5h7sIu72X2piLYlp_TZYRQvBQ,216
+lyrics_transcriber/frontend/vite.config.ts,sha256=EgliYm4wf_nx1mZOx6xx2Hu4aVAgoJ4jdbtsaXfawqI,306
 lyrics_transcriber/frontend/web_assets/android-chrome-192x192.png,sha256=lg-6aPF5mGLiuG7LyftZk_0RI41srmpA8wj-NkaaQms,17632
 lyrics_transcriber/frontend/web_assets/android-chrome-512x512.png,sha256=x-zuKT3NYsTqAWzhKRTZeD4-0uYoUjqMPZpKTChqNJ8,123447
 lyrics_transcriber/frontend/web_assets/apple-touch-icon.png,sha256=6y5vGra54w5oc8VP6sn2JjoQtN9hWTKn0YPhmdlmfU0,16188
@@ -209,7 +215,7 @@ lyrics_transcriber/frontend/web_assets/favicon-32x32.png,sha256=6TyrRMIw6G8dpG4_
 lyrics_transcriber/frontend/web_assets/favicon.ico,sha256=ZK7QvdBuZp0QxPkluCW4IKxfleFmFLp1KkG_d5xmx7E,15406
 lyrics_transcriber/frontend/web_assets/index.html,sha256=qqHYlM3VAy_3YJn3QgETGjR94XTWL3Ci_S-5_lHYgxw,830
 lyrics_transcriber/frontend/web_assets/nomad-karaoke-logo.png,sha256=jTTBFXV6hGJGolZYQ-dIjgQQbMsehk5XGtsllhLrdzg,212641
-lyrics_transcriber/frontend/yarn.lock,sha256=wtImLsCO1P1Lpkhc1jAN6IiHQ0As4xn39n0cwKoh4LM,131996
+lyrics_transcriber/frontend/yarn.lock,sha256=baEFTcZVRQBGZGUKDvzTutfipBZcmoBQvHlM5wxguuc,130621
 lyrics_transcriber/lyrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/lyrics/base_lyrics_provider.py,sha256=SskR5RIKorLcHhNSpHV35_kCnSA027_OOO9E45Jbv88,9168
 lyrics_transcriber/lyrics/file_provider.py,sha256=WNd6mHMV2FhrnHiWBvxUxPkdVi47mbLE4hXaTYqStTM,4290
@@ -262,7 +268,7 @@ lyrics_transcriber/output/fonts/Zurich_Cn_BT_Bold.ttf,sha256=WNG5LOQ-uGUF_WWT5aQ
 lyrics_transcriber/output/fonts/arial.ttf,sha256=NcDzVZ2NtWnjbDEJW4pg1EFkPZX1kTneQOI_ragZuDM,275572
 lyrics_transcriber/output/fonts/georgia.ttf,sha256=fQuyDGMrtZ6BoIhfVzvSFz9x9zIE3pBY_raM4DIicHI,142964
 lyrics_transcriber/output/fonts/verdana.ttf,sha256=lu0UlJyktzks_yNbnEHVXBJTgqu-DA08K53WaJfK4Ms,139640
-lyrics_transcriber/output/generator.py,sha256=jruQv0FQHlVkrLML-rcJqWCR7n5YT1QRE9yDBjqQJy0,11990
+lyrics_transcriber/output/generator.py,sha256=eblMtME-OBTbf1awd9BvlTLyUer_XcIXfIo0L-l38b4,13774
 lyrics_transcriber/output/lrc_to_cdg.py,sha256=2pi5tvreD_ADAR4RF5yVwj7OJ4Pf5Zo_EJ7rt4iH3k0,2063
 lyrics_transcriber/output/lyrics_file.py,sha256=_KQyQjCOMIwQdQ0115uEAUIjQWTRmShkSfQuINPKxaw,3741
 lyrics_transcriber/output/plain_text.py,sha256=XARaWcy6MeQeQCUoz0PV_bHoBw5dba-u79bjS7XucnE,3867
@@ -270,18 +276,19 @@ lyrics_transcriber/output/segment_resizer.py,sha256=rrgcQC28eExSAmGnm6ytkF-E-nH4
 lyrics_transcriber/output/subtitles.py,sha256=TW8IFTedj7-jHDyKKLYk1rFSFmuk8qysrI83Lkc3x-o,19555
 lyrics_transcriber/output/video.py,sha256=n6QtT3ljtx1t8CT9jmVTKSpdezF2gC0FJsYDDtkP5fE,24084
 lyrics_transcriber/review/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-lyrics_transcriber/review/server.py,sha256=_05ul0MsddKf8iTIg-NASVYkl9kBRo0M3WhWBxp79i8,29462
+lyrics_transcriber/review/server.py,sha256=pTeTniQWAeiPxH-I0lnPuAWNY9DyJjFvLIS7nUOYkxk,29459
 lyrics_transcriber/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/storage/dropbox.py,sha256=Dyam1ULTkoxD1X5trkZ5dGp5XhBGCn998moC8IS9-68,9804
 lyrics_transcriber/transcribers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/transcribers/audioshake.py,sha256=RihuLKzhhHfX7m5cjKISwIuTQkGWapCS29D6Qk3hR4U,15869
 lyrics_transcriber/transcribers/base_transcriber.py,sha256=T3m4ZCwZ9Bpv6Jvb2hNcnllk-lmeNmADDJlSySBtP1Q,6480
+lyrics_transcriber/transcribers/local_whisper.py,sha256=oT-MsKdkHMgRpuCdYL4o8vtCZ4Uhls7BzkRDf-QHMHM,9926
 lyrics_transcriber/transcribers/whisper.py,sha256=YcCB1ic9H6zL1GS0jD0emu8-qlcH0QVEjjjYB4aLlIQ,13260
 lyrics_transcriber/types.py,sha256=UJjaxhVd2o14AG4G8ToU598p0JeYdiTFjpG38jGCoYQ,27917
 lyrics_transcriber/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lyrics_transcriber/utils/word_utils.py,sha256=-cMGpj9UV4F6IsoDKAV2i1aiqSO8eI91HMAm_igtVMk,958
-karaoke_gen-0.75.53.dist-info/METADATA,sha256=DR2eCSIs1DM9Xudkimpy66AgxZRfYSYyzpBX-sxkhgE,20662
-karaoke_gen-0.75.53.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-karaoke_gen-0.75.53.dist-info/entry_points.txt,sha256=xIyLe7K84ZyjO8L0_AmNectz93QjGSs5AkApMtlAd4g,160
-karaoke_gen-0.75.53.dist-info/licenses/LICENSE,sha256=81R_4XwMZDODHD7JcZeUR8IiCU8AD7Ajl6bmwR9tYDk,1074
-karaoke_gen-0.75.53.dist-info/RECORD,,
+karaoke_gen-0.81.1.dist-info/METADATA,sha256=zA3O3rRKeXu_LX28aeN3knlhx3WcpXD8Ozf4s_LT2C0,23077
+karaoke_gen-0.81.1.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+karaoke_gen-0.81.1.dist-info/entry_points.txt,sha256=xIyLe7K84ZyjO8L0_AmNectz93QjGSs5AkApMtlAd4g,160
+karaoke_gen-0.81.1.dist-info/licenses/LICENSE,sha256=81R_4XwMZDODHD7JcZeUR8IiCU8AD7Ajl6bmwR9tYDk,1074
+karaoke_gen-0.81.1.dist-info/RECORD,,

lyrics_transcriber/core/config.py

@@ -11,6 +11,14 @@ class TranscriberConfig:
     runpod_api_key: Optional[str] = None
     whisper_runpod_id: Optional[str] = None
 
+    # Local Whisper configuration - reads from environment variables with sensible defaults
+    # Environment variables: WHISPER_MODEL_SIZE, WHISPER_DEVICE, WHISPER_CACHE_DIR, WHISPER_LANGUAGE
+    enable_local_whisper: bool = True  # Enabled by default as fallback
+    local_whisper_model_size: str = field(default_factory=lambda: os.getenv("WHISPER_MODEL_SIZE", "medium"))
+    local_whisper_device: Optional[str] = field(default_factory=lambda: os.getenv("WHISPER_DEVICE"))
+    local_whisper_cache_dir: Optional[str] = field(default_factory=lambda: os.getenv("WHISPER_CACHE_DIR"))
+    local_whisper_language: Optional[str] = field(default_factory=lambda: os.getenv("WHISPER_LANGUAGE"))
+
 
 @dataclass
 class LyricsConfig:

lyrics_transcriber/core/controller.py

@@ -7,6 +7,7 @@ from lyrics_transcriber.types import LyricsData, TranscriptionResult, Correction
 from lyrics_transcriber.transcribers.base_transcriber import BaseTranscriber
 from lyrics_transcriber.transcribers.audioshake import AudioShakeTranscriber, AudioShakeConfig
 from lyrics_transcriber.transcribers.whisper import WhisperTranscriber, WhisperConfig
+from lyrics_transcriber.transcribers.local_whisper import LocalWhisperTranscriber, LocalWhisperConfig
 from lyrics_transcriber.lyrics.base_lyrics_provider import BaseLyricsProvider, LyricsProviderConfig
 from lyrics_transcriber.lyrics.genius import GeniusProvider
 from lyrics_transcriber.lyrics.spotify import SpotifyProvider
@@ -206,6 +207,34 @@ class LyricsTranscriber:
         else:
             self.logger.debug("Skipping Whisper transcriber - missing runpod_api_key or whisper_runpod_id")
 
+        # Local Whisper - lowest priority, fallback when cloud services unavailable
+        if self.transcriber_config.enable_local_whisper:
+            # Check if whisper-timestamped is available
+            try:
+                import whisper_timestamped  # noqa: F401
+
+                self.logger.debug("Initializing LocalWhisper transcriber")
+                transcribers["local_whisper"] = {
+                    "instance": LocalWhisperTranscriber(
+                        cache_dir=self.output_config.cache_dir,
+                        config=LocalWhisperConfig(
+                            model_size=self.transcriber_config.local_whisper_model_size,
+                            device=self.transcriber_config.local_whisper_device,
+                            cache_dir=self.transcriber_config.local_whisper_cache_dir,
+                            language=self.transcriber_config.local_whisper_language,
+                        ),
+                        logger=self.logger,
+                    ),
+                    "priority": 3,  # Local Whisper has lowest priority (fallback)
+                }
+            except ImportError:
+                self.logger.debug(
+                    "Skipping LocalWhisper transcriber - whisper-timestamped not installed. "
+                    "Install with: pip install karaoke-gen[local-whisper]"
+                )
+        else:
+            self.logger.debug("Skipping LocalWhisper transcriber - disabled via enable_local_whisper=False")
+
         return transcribers
 
     def _initialize_lyrics_providers(self) -> Dict[str, BaseLyricsProvider]:
@@ -442,7 +471,7 @@ class LyricsTranscriber:
         # Whisper/RunPod status
         has_runpod_key = bool(self.transcriber_config.runpod_api_key)
         has_whisper_id = bool(self.transcriber_config.whisper_runpod_id)
-        
+
         if has_runpod_key and has_whisper_id:
             self.logger.debug("  - Whisper (RunPod): CONFIGURED (API key and endpoint ID provided)")
         elif has_runpod_key:
@@ -452,6 +481,19 @@ class LyricsTranscriber:
         else:
             self.logger.debug("  - Whisper (RunPod): NOT CONFIGURED (missing RUNPOD_API_KEY and WHISPER_RUNPOD_ID)")
 
+        # Local Whisper status
+        if self.transcriber_config.enable_local_whisper:
+            try:
+                import whisper_timestamped  # noqa: F401
+                self.logger.debug(
+                    f"  - LocalWhisper: AVAILABLE (model={self.transcriber_config.local_whisper_model_size}, "
+                    f"device={self.transcriber_config.local_whisper_device or 'auto'})"
+                )
+            except ImportError:
+                self.logger.debug("  - LocalWhisper: ENABLED but whisper-timestamped not installed")
+        else:
+            self.logger.debug("  - LocalWhisper: DISABLED (enable_local_whisper=False)")
+
     def correct_lyrics(self) -> None:
         """Run lyrics correction using transcription and internet lyrics."""
         self.logger.info("Starting lyrics correction process")

lyrics_transcriber/correction/agentic/providers/config.py

@@ -18,6 +18,10 @@ class ProviderConfig:
     privacy_mode: bool
     cache_dir: str
 
+    # GCP/Vertex AI settings
+    gcp_project_id: Optional[str] = None
+    gcp_location: str = "us-central1"
+
     request_timeout_seconds: float = 30.0
     max_retries: int = 2
     retry_backoff_base_seconds: float = 0.2
@@ -46,6 +50,8 @@ class ProviderConfig:
             openrouter_api_key=os.getenv("OPENROUTER_API_KEY"),
             privacy_mode=os.getenv("PRIVACY_MODE", "false").lower() in {"1", "true", "yes"},
             cache_dir=cache_dir,
+            gcp_project_id=os.getenv("GOOGLE_CLOUD_PROJECT") or os.getenv("GCP_PROJECT_ID"),
+            gcp_location=os.getenv("GCP_LOCATION", "us-central1"),
             request_timeout_seconds=float(os.getenv("AGENTIC_TIMEOUT_SECONDS", "30.0")),
             max_retries=int(os.getenv("AGENTIC_MAX_RETRIES", "2")),
             retry_backoff_base_seconds=float(os.getenv("AGENTIC_BACKOFF_BASE_SECONDS", "0.2")),

lyrics_transcriber/correction/agentic/providers/model_factory.py

@@ -155,6 +155,8 @@ class ModelFactory:
                 return self._create_openai_model(model_name, callbacks, config)
             elif provider == "anthropic":
                 return self._create_anthropic_model(model_name, callbacks, config)
+            elif provider in ("vertexai", "google"):
+                return self._create_vertexai_model(model_name, callbacks, config)
             else:
                 raise ValueError(f"Unsupported provider: {provider}")
         except ImportError as e:
@@ -197,7 +199,7 @@ class ModelFactory:
     ) -> Any:
         """Create ChatAnthropic model."""
         from langchain_anthropic import ChatAnthropic
-        
+
         model = ChatAnthropic(
             model=model_name,
             timeout=config.request_timeout_seconds,
@@ -207,3 +209,24 @@ class ModelFactory:
         logger.debug(f"🤖 Created Anthropic model: {model_name}")
         return model
 
+    def _create_vertexai_model(
+        self, model_name: str, callbacks: List[Any], config: ProviderConfig
+    ) -> Any:
+        """Create ChatVertexAI model for Google Gemini via Vertex AI.
+
+        Uses Application Default Credentials (ADC) for authentication.
+        In Cloud Run, this uses the service account automatically.
+        Locally, run: gcloud auth application-default login
+        """
+        from langchain_google_vertexai import ChatVertexAI
+
+        model = ChatVertexAI(
+            model=model_name,
+            project=config.gcp_project_id,
+            location=config.gcp_location,
+            max_retries=config.max_retries,
+            callbacks=callbacks,
+        )
+        logger.debug(f"🤖 Created Vertex AI model: {model_name} (project={config.gcp_project_id})")
+        return model
+

lyrics_transcriber/correction/agentic/router.py

@@ -5,6 +5,9 @@ from typing import Dict, Any
 
 from .providers.config import ProviderConfig
 
+# Default model for cloud deployments - Gemini 3 Flash via Vertex AI
+DEFAULT_CLOUD_MODEL = "vertexai/gemini-3-flash-preview"
+
 
 class ModelRouter:
     """Rules-based routing by gap type/length/uncertainty (scaffold)."""
@@ -14,22 +17,23 @@ class ModelRouter:
 
     def choose_model(self, gap_type: str, uncertainty: float) -> str:
         """Choose appropriate model based on gap characteristics.
-        
+
         Returns model identifier in format "provider/model" for LangChain:
-        - "ollama/gpt-oss:latest" for local Ollama models
-        - "openai/gpt-4" for OpenAI models  
+        - "vertexai/gemini-3-flash-preview" for Gemini via Vertex AI (default)
+        - "ollama/llama3.2:latest" for local Ollama models
+        - "openai/gpt-4" for OpenAI models
         - "anthropic/claude-3-sonnet-20240229" for Anthropic models
         """
-        # Simple baseline per technical guidance
+        # Check for explicit model override from environment
+        env_model = os.getenv("AGENTIC_AI_MODEL")
+        if env_model:
+            return env_model
+
+        # Privacy mode: use local Ollama
         if self._config.privacy_mode:
-            # Use the actual model from env, or default to a common Ollama model
-            return os.getenv("AGENTIC_AI_MODEL", "ollama/gpt-oss:latest")
-        
-        # For high-uncertainty gaps, use Claude (best reasoning)
-        if uncertainty > 0.5:
-            return "anthropic/claude-3-sonnet-20240229"
-        
-        # Default to GPT-4 for general cases
-        return "openai/gpt-4"
+            return "ollama/llama3.2:latest"
+
+        # Default to Gemini 3 Flash for all cases (fast, cost-effective)
+        return DEFAULT_CLOUD_MODEL
 
 

lyrics_transcriber/frontend/.gitignore

@@ -21,3 +21,4 @@ dist-ssr
 *.njsproj
 *.sln
 *.sw?
+test-results/