justin/shorts-autopilot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto install narration and image dependencies, add Kokoro narration engine

Browse Source
This commit is contained in:
Justin Oros
2026-09-20 16:44:32 -07:00
parent 8dd632100c
commit cb17055320
2 changed files with 153 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
static/index.html
+4 -3
View File
@@ -126,6 +126,7 @@ const FIELDS=[
["temp_dir","Temp folder","wide","Scratch space used while rendering. Blank puts it in the storage folder","g"],
["delete_after_publish","Delete videos after publishing","checkbox","Removes the job folder once the upload succeeds instead of moving it to published","g"],
["keep_clips","Keep individual clips","checkbox","Keeps the scene clips, images, and narration alongside final.mp4","g"],
["auto_install","Install missing pieces automatically","checkbox","Downloads models and installs packages when a run needs them","g"],
["","Video engine (shared by all profiles)","header","",""],
["video_engine","Video engine","select:local=Local (free: AI images, narration, motion)|veo=Veo (paid Google API)","Local runs entirely on this machine at no cost. Veo makes true AI video but needs billing","g"],
["sd_model","Image model","text","Hugging Face model id, e.g. stabilityai/sdxl-turbo or stabilityai/stable-diffusion-xl-base-1.0","g"],
@@ -133,9 +134,9 @@ const FIELDS=[
["sd_guidance","Image guidance","number","0 for turbo models, 7 for standard models","g"],
["sd_width","Image width","number","768 avoids duplicated subjects. Larger is slower","g"],
["sd_height","Image height","number","1344 is the correct vertical ratio for SDXL","g"],
["tts_engine","Narration engine","select:auto=Auto|piper=Piper (natural)|say=macOS say|espeak=espeak-ng","Auto uses Piper when a voice file is present, otherwise the system voice","g"],
["tts_voice","Narration voice","text","macOS: Samantha, Alex, Daniel. espeak: en-us","g"],
["tts_rate","Narration speed","number","macOS words per minute (170). espeak uses a similar scale","g"],
["tts_engine","Narration engine","select:auto=Auto (best available)|kokoro=Kokoro (most natural)|piper=Piper|say=macOS say|espeak=espeak-ng","Missing engines are installed automatically on the next run","g"],
["tts_voice","Narration voice","text","Kokoro: af_heart, af_bella, am_michael, bf_emma. Ignored by the system voice","g"],
["tts_rate","Narration speed","number","Only used by the system voice. Words per minute","g"],
["piper_model","Piper voice file","wide","Blank uses the first voice found in the voices folder under Models","g"],
["gemini_api_key","Gemini API key (Veo)","password","Only needed for the Veo engine. Billing must be enabled","g"],
["veo_model","Veo model","text","e.g. veo-3.1-fast-generate-preview","g"],