Sonicaura Mcp

io.github.warmcodingv1.0.0更新于 Oct 11, 2026

Remote MCP server for audio stem separation, denoise, and reverb.

已验证Streamable HTTP可网页运行Media & Design

概览

AI 生成的概览

一个远程 MCP 服务器，让助手把音频分离成人声、鼓、贝斯等音轨，去除噪声并添加混响。

功能
SonicAura 通过远程端点提供 GPU 加速的音频处理。其工具可以列出可用任务类型、检查服务状态与剩余额度、获取预签名上传链接或直接以 base64 上传小文件、提交处理任务，并轮询任务进度。支持的任务包括分离为 2、4 或 6 条音轨、音乐降噪、语音强力降噪，以及带人声棚、录音室、音乐厅等预设的混响。
适用场景
适合助手需要处理音频素材的场景：从歌曲中分离人声、鼓、贝斯、吉他或钢琴，生成伴奏，清理音乐或人声录音中的噪声，或为人声添加空间混响。适用于音乐、播客和配音工作流，前提是音频可以发送到托管服务。
运行要求
需要一个远程 Streamable HTTP 端点 MCP 客户端配置。认证方式为 OAuth 2.0。需要网络访问，处理会消耗服务额度，工具可查询剩余额度。
安装前请注意
音频文件会上传到第三方托管服务，除非可以接受，否则不要发送机密或未发布的素材。处理会消耗额度，较大文件通过预签名上传链接传输。任务为异步提交与轮询，结果依赖远程服务可用性。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Sonicaura Mcp，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "sonicaura-mcp": {
      "type": "http",
      "url": "https://api.sonicaurastudio.com/mcp"
    }
  }
}

README

[SonicAura Logo]

[Smithery]

sonicaura-mcp

Remote MCP server for audio stem separation, denoise, and reverb.

What it does

SonicAura processes audio using GPU-accelerated AI:

  • Stem separation — split a track into 2, 4, or 6 stems
    • 2stems: vocals + no_vocals
    • 4stems: vocals + drums + bass + other
    • 6stems: vocals + guitar + bass + drums + piano + other
  • Denoise
    • music_denoise: remove noise from music while keeping the instruments and vocals intact
    • denoise: aggressive speech cleanup for podcasts / interviews / voiceovers
  • Reverb — add spatial reverb with presets: vocal_booth, studio_room, bathroom, concert_hall, church

Endpoint

https://api.sonicaurastudio.com/mcp

Transport: http (Streamable HTTP) Auth: OAuth 2.0

Tools

ToolDescription
list_audio_toolsList available task types and metadata
check_service_statusConfirm service availability and credits
get_upload_urlPresigned URL for files larger than 1 MB
upload_audioBase64 upload for files under 1 MB
process_audioSubmit a task (music_denoise | denoise | reverb | 2stems | 4stems | 6stems)
check_task_statusPoll a task
get_my_creditsCheck remaining credits

Usage

Add the server to your MCP client config:

{  "mcpServers": {    "audio-process": {      "type": "http",      "url": "https://api.sonicaurastudio.com/mcp"    }  }}

Then ask your client things like:

  • "Extract the vocals from this song"
  • "Remove the vocals and keep the instrumental"
  • "Separate this song into 6 stems"
  • "Isolate the guitar track"
  • "Denoise this music but keep the background music"
  • "Clean up the noise in this voice recording"
  • "Add studio reverb to this vocal"

Credits

Processing uses credits. Get an account and credits at https://www.sonicaurastudio.com

License

MIT

来源：README.md，提交 38fba3b

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v1.0.0最新Oct 11, 2026