Skip to content

Fix #647: Add: Step_Audio_EditX_TTS, FishAudioS2, SoulX-Singer & Stab...#659

Open
JiwaniZakir wants to merge 1 commit into
rsxdalv:mainfrom
JiwaniZakir:fix/647-add-step-audio-editx-tts-fishaudios2-sou
Open

Fix #647: Add: Step_Audio_EditX_TTS, FishAudioS2, SoulX-Singer & Stab...#659
JiwaniZakir wants to merge 1 commit into
rsxdalv:mainfrom
JiwaniZakir:fix/647-add-step-audio-editx-tts-fishaudios2-sou

Conversation

@JiwaniZakir

Copy link
Copy Markdown

Closes #647

Before

extensions.json contained no entries for Step-Audio EditX TTS or Fish Audio S2 in the text-to-speech section, and no entries for SoulX Singer or StableAudioX in the audio-music-generation section. Users had no way to install these four models through the TTS WebUI extension manager.

After

Four new extension entries are registered in extensions.json:

text-to-speech section (after the megatts3 entry, lines ~503–528):

  • tts_webui_extension.step_audio_editx_tts — Step-Audio EditX TTS (Beta), backed by stepfun-ai/Step-Audio, installed from rsxdalv/tts_webui_extension.step_audio_editx_tts@main
  • tts_webui_extension.fish_audio_s2 — Fish Audio S2 (Beta), backed by fishaudio/fish-speech, installed from rsxdalv/tts_webui_extension.fish_audio_s2@main

audio-music-generation section (after the songbloom entry, lines ~633–658):

  • tts_webui_extension.soulx_singer — SoulX Singer (Beta), installed from rsxdalv/tts_webui_extension.soulx_singer@main
  • tts_webui_extension.stable_audio_x — StableAudioX (Beta), backed by Stability AI's AudioX model, installed from rsxdalv/tts_webui_extension.stable_audio_x@main

All four entries are marked Beta, use "extension_type": "interface", carry MIT licenses, and follow the existing schema structure (package_name, name, requirements, description, extension_type, extension_class, author, extension_author, license, website, extension_website, extension_platform_version).

Changes

  • extensions.json: Added 2 entries to text-to-speech array and 2 entries to audio-music-generation array. No other files modified.

Testing

  1. Load the extension manager in TTS WebUI and confirm all four extensions appear in their respective categories.
  2. Install each extension individually and verify the pip install resolves against the correct @main branch of each rsxdalv/tts_webui_extension.* repo.
  3. Confirm JSON validity: python -m json.tool extensions.json exits 0.

This PR was created with AI assistance (Claude). The changes were reviewed by quality gates and a critic model before submission.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@rsxdalv

rsxdalv commented Apr 16, 2026

Copy link
Copy Markdown
Owner

Hi, I appreciate the attention, but external extensions allow for such installations. For 2026 modifying extensions.json is mainly not going to happen.
Recent extensions live on https://rsxdalv.github.io/tts-webui-extension-catalog/?browse=true which can be opened from TTS WebUI's "extensions" tab and allows for direct installation, which will add the json metadata to extensions.external.json and load up.
Furthermore, the PR references extensions that do not exist, such as: rsxdalv/tts_webui_extension.soulx_singer (none of the mentioned ones exist) so this is not usable until all of those extensions get implemented.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add: Step_Audio_EditX_TTS, FishAudioS2, SoulX-Singer & StableAudioX

2 participants