Ethanfel/ComfyUI-Omnivoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
39 Commits 1 Branch 1 Tag
46591553f93a0834d91baf1626565f1e951fd03a
Commit Graph

8 Commits

Author SHA1 Message Date
Ethanfel 46591553f9 feat: add torch.compile option to Model Loader 
Compiles the model graph on first generation (~30-60s warmup) then
speeds up all subsequent generations in the session. Recommended for
audiobook pipelines. Default off.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 19:16:39 +02:00
Ethanfel 2e1cba61fc fix: adjust node sizes in default workflow for seed widget 
Generate node height 340→400 to fit all 6 widgets, Voice Preset
height 80→100, SaveAudio position adjusted.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 19:12:31 +02:00
Ethanfel c22cc7c296 rename: voice_cloning.json → omnivoice_voice_cloning.json 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 19:10:51 +02:00
Ethanfel f8a3bebe9c feat: add seed=42 to default workflow for voice consistency 
Sets a default seed so the voice stays consistent across all generated
chunks when using the workflow as a starting point for audiobook pipelines.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 18:58:22 +02:00
Ethanfel 4c42322c6f Expand voice presets to 8 voices (3 female, 5 male) 
All transcribed via whisper-medium. Sources: Chatterbox demo GCS bucket
(ResembleAI) and F5-TTS repo (SWivid).

Female: Shadowheart, American actress, Podcast host
Male: Nature, Old Hollywood, Rick Sanchez, Stewie Griffin,
      Harvey Keitel, Conan O'Brien

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 18:51:43 +02:00
Ethanfel 8de201a4c9 Add OmniVoice Voice Preset node with two female voice samples 
Two built-in presets, auto-downloaded and cached to ComfyUI/models/omnivoice/presets/:
- "Nature – female, warm" (F5-TTS basic_ref_en.wav, transcript included)
- "Shadowheart – female, expressive" (Chatterbox demo, connect Whisper for transcript)

Outputs ref_audio (AUDIO) and ref_text (STRING) — wire directly into
OmniVoice Generate. Updated default workflow to use this node.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 18:19:29 +02:00
Ethanfel b52edcfd84 Remove local path option from model loader 
Models always download to ComfyUI/models/omnivoice/ via HuggingFace.
Local path added unnecessary complexity; users who want a custom path
can symlink into the models directory.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 18:02:55 +02:00
Ethanfel cd0f7aff07 Add default voice cloning workflow 
Model Loader → Load Audio → OmniVoice Generate → Save Audio.
Connect a Whisper node to ref_text for auto-transcription.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-05 18:01:18 +02:00