Skip to content

alteradas - #4390

Closed
dansfisica85 wants to merge 52 commits into
coqui-ai:devfrom
dansfisica85:dev
Closed

alteradas#4390
dansfisica85 wants to merge 52 commits into
coqui-ai:devfrom
dansfisica85:dev

Conversation

@dansfisica85

Copy link
Copy Markdown

No description provided.

Copilot AI review requested due to automatic review settings January 16, 2026 16:08
@CLAassistant

Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

@dansfisica85

Copy link
Copy Markdown
Author

ok

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This pull request adds voice cloning and AI cover generation capabilities to the TTS project. It introduces new modules for audio separation, voice conversion, and mixing, along with automated training workflows and web interfaces.

Changes:

  • Added RVC (Retrieval-based Voice Conversion) integration for voice conversion
  • Created automated AI cover generation pipeline with audio separation and mixing
  • Updated Python version requirements from 3.9-3.11 to 3.9-3.12
  • Added new utility scripts and batch installer for Windows

Reviewed changes

Copilot reviewed 13 out of 15 changed files in this pull request and generated 5 comments.

Show a summary per file
File Description
voice_converter.py New module for RVC-based voice conversion with model loading and audio processing
setup.py Updated Python version constraint to support 3.12
rvc Added RVC submodule reference
requirements.txt Updated numba version constraints for Python 3.12 compatibility and pandas >=2.0
instalar.bat New Windows batch installer script
clonar_voz.py New voice cloning script with XTTS v2 model and Gradio interface
audio_separator.py New audio separation module using Demucs
audio_mixer.py New audio mixing utilities for combining vocals and instrumentals
ai_cover_app.py New automated AI cover generation application with training workflow
TTS/demos/xtts_ft_demo/xtts_demo.py Replaced os.system with shutil.copy for better cross-platform compatibility
README_CLONADOR.md New documentation for voice cloning features
.gradio/certificate.pem Added SSL certificate for Gradio
Comments suppressed due to low confidence (1)

audio_separator.py:1

  • The docstring states 'Sem dependência de torchaudio ou FFmpeg' but line 15 imports torch, and the module uses torch tensors throughout. While it avoids torchaudio for loading/saving, the documentation should clarify that PyTorch is still required.
#!/usr/bin/env python

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread voice_converter.py
Comment thread instalar.bat Outdated
Comment thread clonar_voz.py
Comment thread ai_cover_app.py Outdated
Comment thread ai_cover_app.py Outdated
…ploads no Gradio

- Adicionar gradio_config.py com configurações otimizadas
- Criar upload_handler.py com validação e lógica de retry
- Atualizar ai_cover_app.py com validação de uploads e logging
- Modificar Dockerfile para incluir variáveis de ambiente
- Incluir documentação abrangente e testes
…m som

- Adiciona logs detalhados em cada etapa do processo
- Normaliza vocal quando muito baixo após separação
- Melhora mensagem de sucesso com nível de áudio e tamanho do arquivo
- Adiciona dicas de troubleshooting na mensagem final
@dansfisica85

Copy link
Copy Markdown
Author

@copilot open a new pull request to apply changes based on the comments in this thread

@dansfisica85

Copy link
Copy Markdown
Author

@copilot open a new pull request to apply changes based on the comments in this thread

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.

3 participants