lulavc commited on
Commit
673f772
·
1 Parent(s): 34fc3ab

fix: force wav format on audio inputs to fix recording on Linux/webm browsers

Browse files
Files changed (1) hide show
  1. app.py +4 -1
app.py CHANGED
@@ -447,6 +447,7 @@ with gr.Blocks(title="AnimaStudio 🎬") as demo:
447
  voice_ref = gr.Audio(
448
  label="Voice Reference (optional — clone voice style)",
449
  type="filepath", sources=["upload", "microphone"],
 
450
  )
451
  emotion = gr.Slider(0.0, 1.0, value=0.5, step=0.05,
452
  label="Emotion Intensity", info="0 = neutral · 1 = very expressive")
@@ -454,6 +455,7 @@ with gr.Blocks(title="AnimaStudio 🎬") as demo:
454
  audio_upload = gr.Audio(
455
  label="Audio File · WAV/MP3/FLAC · max 30 s",
456
  type="filepath", sources=["upload", "microphone"],
 
457
  )
458
  aspect_ratio = gr.Dropdown(choices=list(ASPECT_PRESETS.keys()),
459
  value="◻ 1:1 · 512×512", label="Format")
@@ -478,7 +480,8 @@ with gr.Blocks(title="AnimaStudio 🎬") as demo:
478
  sources=["upload"])
479
  dub_target_lang = gr.Dropdown(choices=TTS_LANGUAGES, value="English", label="Target Language")
480
  dub_voice_ref = gr.Audio(label="Voice Reference (optional — clone voice style)",
481
- type="filepath", sources=["upload", "microphone"])
 
482
  dub_emotion = gr.Slider(0.0, 1.0, value=0.5, step=0.05, label="Emotion Intensity")
483
  dub_btn = gr.Button("🎙️ Dub Video", variant="primary", elem_id="dub-btn", size="lg")
484
  gr.HTML("""
 
447
  voice_ref = gr.Audio(
448
  label="Voice Reference (optional — clone voice style)",
449
  type="filepath", sources=["upload", "microphone"],
450
+ format="wav",
451
  )
452
  emotion = gr.Slider(0.0, 1.0, value=0.5, step=0.05,
453
  label="Emotion Intensity", info="0 = neutral · 1 = very expressive")
 
455
  audio_upload = gr.Audio(
456
  label="Audio File · WAV/MP3/FLAC · max 30 s",
457
  type="filepath", sources=["upload", "microphone"],
458
+ format="wav",
459
  )
460
  aspect_ratio = gr.Dropdown(choices=list(ASPECT_PRESETS.keys()),
461
  value="◻ 1:1 · 512×512", label="Format")
 
480
  sources=["upload"])
481
  dub_target_lang = gr.Dropdown(choices=TTS_LANGUAGES, value="English", label="Target Language")
482
  dub_voice_ref = gr.Audio(label="Voice Reference (optional — clone voice style)",
483
+ type="filepath", sources=["upload", "microphone"],
484
+ format="wav")
485
  dub_emotion = gr.Slider(0.0, 1.0, value=0.5, step=0.05, label="Emotion Intensity")
486
  dub_btn = gr.Button("🎙️ Dub Video", variant="primary", elem_id="dub-btn", size="lg")
487
  gr.HTML("""