Added support for Fish Audio S2.1#152
Conversation
|
Important Review skippedAuto reviews are disabled on this repository. To trigger a review, include ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches✨ Simplify code
Comment |
Resolve import conflict in clientlibs/main.js by combining handlers from both branches (MeshCluster, Moodboards from main; ReferenceVoice from feature-FishAudio).
There was a problem hiding this comment.
Pull request overview
This PR adds Fish Audio S2.1 Pro support to the Runware ComfyUI integration by introducing a new model option, expanding audio settings to cover additional Fish-related parameters, and adding a new node to supply inputs.referenceVoices (reference audio + transcript) for zero-shot voice cloning.
Changes:
- Added “Fish” as an audio model provider and included the
fishaudio:s2.1@promodel option in both backend and UI filtering. - Expanded the Audio Inference Settings node to expose additional generation parameters (e.g.,
topP,chunkLength,maxTokens, etc.) and wired corresponding UI toggles. - Added a new “Runware Audio Inference Inputs Reference Audio” node and a new workflow demonstrating Fish S2.1 usage.
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| workflows/Runware_Audio_Inference_Fish_S_2_1.json | Adds a ready-to-use workflow showcasing Fish S2.1 Pro with reference audio wiring. |
| modules/audioSettings.py | Adds new optional audio generation settings fields and includes them in settings payload construction. |
| modules/audioModelSearch.py | Adds Fish provider and Fish S2.1 Pro model to the backend model list. |
| modules/audioInferenceReferenceVoices.py | Introduces a new node producing inputs.referenceVoices from up to 4 reference audio/text pairs. |
| modules/audioInferenceInputs.py | Adds an optional input socket to accept referenceVoices and include it in inputs. |
| clientlibs/utils.js | Adds UI toggling for the new audio settings fields and the new reference-audio node’s widgets. |
| clientlibs/types.js | Registers the new node type for UI styling/configuration. |
| clientlibs/main.js | Hooks the new node type into the UI initialization/toggle handler flow. |
| init.py | Registers the new node in the Python node class mappings. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Uh oh!
There was an error while loading. Please reload this page.