RRepoGEO

REPOGEO 报告 · LITE

PlayVoice/whisper-vits-svc

默认分支 bigvgan-mix-v2 · commit b95a8495 · 扫描时间 2026/6/21 18:26:56

星标 2,858 · Fork 912

本仓库扫描历史

下方为分数趋势(含全部就绪扫描;左旧右新,可横向滚动)。表格明细默认折叠,展开后每页 10 条,最新在上。

分数趋势(左 → 右:旧 → 新)

共 2 条就绪扫描。点击下方按钮展开表格(每页 10 条,可翻页)。

AI 可见性总分
33 /100
亟需修复
品类召回
0 / 2
在所有问题中均未被推荐
规则结果
通过 2 · 警告 0 · 失败 0
客观元数据检查
AI 认识你的名字
2 / 3
直接询问时,AI 是否点名你的仓库
如何阅读这份报告

行动计划告诉你下一步要做什么——按影响力排序、可直接复制粘贴的修改。品类可见性是真正的 GEO 测试:当用户向 AI 提一个不带品牌、本应让 PlayVoice/whisper-vits-svc 浮出水面的问题时,AI 是真的推荐了你,还是推荐了你的竞品?客观检查验证 AI 引擎最先权衡的那些元数据信号。自指检查判断 AI 是否还认识你的名字。

行动计划 — 可复制粘贴的修复

3 条由 gemini-2.5-flash 生成、按优先级排序的修改。修完后请把对应条目标记为完成。

整体方向
  • highreadme#1
    Reposition the README's opening to clearly state its purpose and audience

    原因:

    当前
    <h1> Variational Inference with adversarial learning for end-to-end Singing Voice Conversion based on VITS </h1>
        
    [](https://huggingface.co/spaces/maxmax20160403/sovits5.0)
    
    [中文文档](./README_ZH.md)
    
    The tree bigvgan-mix-v2 has good audio quality
    
    The tree RoFormer-HiFTNet has fast infer speed
    
    No More Upgrade
    
    </div>
    
    - This project targets deep learning beginners, basic knowledge of Python and PyTorch are the prerequisites for this project;
    - This project aims to help deep learning beginners get rid of boring pure theoretical learning, and master the basic knowledge of deep learning by combining it with practices;
    - This project does not support real-time voice converting; (need to replace whisper if real-time voice converting is what you are looking for)
    - This project will not develop one-click packages for other purposes;
    复制粘贴的修复
    # PlayVoice/whisper-vits-svc: End-to-End Singing Voice Conversion for Deep Learning Beginners
    
    This project provides a core engine for end-to-end Singing Voice Conversion (SVC) and Singing Voice Clone (SVC) based on VITS, specifically designed to help deep learning beginners master practical skills. It enables users to transform spoken audio into a singing voice, create unique voices by mixing speakers, and even convert voices with light accompaniment.
  • mediumtopics#2
    Expand topics to include specific use cases and target audience

    原因:

    当前
    ["change", "diff-svc", "diffusion", "diffusion-svc", "singing-voice-conversion", "sovits", "svc", "vits", "vits2", "voice"]
    复制粘贴的修复
    ["change", "diff-svc", "diffusion", "diffusion-svc", "singing-voice-conversion", "sovits", "svc", "vits", "vits2", "voice", "singing-voice-synthesis", "deep-learning-for-beginners", "speaker-mixing", "voice-cloning-for-beginners", "audio-synthesis"]
  • lowreadme#3
    Add a dedicated section highlighting key differentiators

    原因:

    复制粘贴的修复
    ## Key Differentiators
    
    PlayVoice/whisper-vits-svc stands out by:
    - **Empowering Beginners:** Designed for deep learning novices, offering a practical approach to mastering voice conversion.
    - **Flexible Speaker Creation:** Supports multiple speakers and allows creating unique voices through speaker mixing.
    - **Accompaniment Handling:** Capable of converting voices even with light background accompaniment.
    - **F0 Editing:** Provides the unique ability to edit F0 using Excel for fine-grained control.

本次扫描解析到的品类 GEO 通道:google/gemini-2.5-flash, deepseek/deepseek-v4-flash

品类可见性 — 真正的 GEO 测试

向 google/gemini-2.5-flash 提出的不带品牌问题。AI 推荐了你,还是推荐了别人?

各模型使用同一组问题 — 切换标签对比回答与排名。

召回
0 / 2
0% 的问题里出现了 PlayVoice/whisper-vits-svc
平均排名
越小越好。#1 表示首位推荐。
声量占比
0%
在所有被点名的工具中,你占了多少?
头号对手
DiffSinger
在 2 个问题中被推荐 1 次
竞品排行
  1. DiffSinger · 被推荐 1 次
  2. OpenVPI · 被推荐 1 次
  3. Tacotron 2 · 被推荐 1 次
  4. FastSpeech 2 · 被推荐 1 次
  5. WaveNet · 被推荐 1 次
  • 品类问题
    Looking for a deep learning model to transform spoken audio into a singing voice.
    你:未被推荐
    AI 推荐顺序:
    1. DiffSinger
    2. OpenVPI
    3. Tacotron 2
    4. FastSpeech 2
    5. WaveNet
    6. WaveGlow
    7. Hifi-GAN
    8. RVC
    9. ESPnet
    10. NVIDIA NeMo
    11. DDSP

    AI 推荐了 11 个替代方案,却始终没点名 PlayVoice/whisper-vits-svc。这就是要补上的差距。

    查看 AI 完整回答
  • 品类问题
    How can I generate unique singing voices by mixing different speaker characteristics for beginners?
    你:未被推荐
    AI 推荐顺序:
    1. Vocaloid
    2. Synthesizer V
    3. UTAU
    4. Vocaloid 6
    5. Synthesizer V Studio Pro
    6. FL Studio
    7. Newtone
    8. Pitcher
    9. iZotope Nectar
    10. Antares Auto-Tune Pro
    11. MAutoPitch
    12. FL Studio 21
    13. iZotope Nectar 4
    14. Antares Auto-Tune Pro X
    15. Adobe Audition
    16. Audacity
    17. Waves Vocal Bender
    18. Little AlterBoy
    19. Voicemod
    20. MorphVOX Pro
    21. Clownfish Voice Changer
    22. ElevenLabs
    23. Google Cloud Text-to-Speech
    24. Descript

    AI 推荐了 24 个替代方案,却始终没点名 PlayVoice/whisper-vits-svc。这就是要补上的差距。

    查看 AI 完整回答

客观检查

针对 AI 引擎最看重的元数据信号的规则审计。

  • Metadata completeness
    pass

  • README presence
    pass

自指检查

当被直接问到你时,AI 是否还知道你的仓库存在?

  • Compared to common alternatives in this category, what is the core differentiator of PlayVoice/whisper-vits-svc?
    pass
    AI 未点名 PlayVoice/whisper-vits-svc —— 很可能在说另一个项目

    AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?

  • If a team adopts PlayVoice/whisper-vits-svc in production, what risks or prerequisites should they evaluate first?
    pass
    AI 明确点名了 PlayVoice/whisper-vits-svc

    AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?

  • In one sentence, what problem does the repo PlayVoice/whisper-vits-svc solve, and who is the primary audience?
    pass
    AI 明确点名了 PlayVoice/whisper-vits-svc

    AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?

嵌入你的 GEO 徽章

把这个徽章贴进 PlayVoice/whisper-vits-svc 的 README。每次重新扫描都会自动更新,并跳到最新报告——是「我在乎 AI 可发现性」最简单的公开证明。

RepoGEO badge preview实时预览
MARKDOWN(README)
[![RepoGEO](https://repogeo.com/badge/PlayVoice/whisper-vits-svc.svg)](https://repogeo.com/zh/r/PlayVoice/whisper-vits-svc)
HTML
<a href="https://repogeo.com/zh/r/PlayVoice/whisper-vits-svc"><img src="https://repogeo.com/badge/PlayVoice/whisper-vits-svc.svg" alt="RepoGEO" /></a>
Pro

订阅 Pro,解锁深度诊断

PlayVoice/whisper-vits-svc — 轻量扫描仍免费;本卡列出 Pro 相对轻量的深度额度。

  • 深度报告每月 10 次
  • 无品牌品类查询5,轻量 2
  • 优先行动项8,轻量 3