Use kokoro-onnx for narration and tighten the source language filter
This commit is contained in:
+1
-1
@@ -143,7 +143,7 @@ const FIELDS=[
|
||||
["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 (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_voice","Narration voice","text","Kokoro: af_heart, af_bella, af_nicole, 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"],
|
||||
|
||||
Reference in New Issue
Block a user