AudioPod AI

ai.audiopod由 audiopod.ai 发布官方发布者v2026.10.14更新于 Oct 24, 2026

Audio AI tools: transcription with speakers, stems, noise removal, MIDI, speech, voices and music.

已验证Streamable HTTP可网页运行媒体与设计AI 与机器学习

概览

AI 生成的概览

托管式 AudioPod MCP 服务器，为助手提供音频 AI 工具：转写、分轨、降噪、声音克隆、语音合成与音乐生成。

可以做什么
  • 转写音频，提供词级时间戳、说话人标签以及 SRT/VTT 字幕，并可将不同说话人分离到独立音轨
  • 把曲目拆分为人声、鼓、贝斯等分轨（双轨模式即卡拉 OK），去除背景噪声，转换音频/视频格式，并将录音转为 MIDI
  • 以 200 多种语言、500 多种音色生成语音，用 5–30 秒参考片段克隆音色，或把录音转换为其他音色
  • 根据文本提示生成歌曲、伴奏或人声分轨，并可创作、读取、修改和录制歌曲乐谱
  • 轮询长时间任务的状态，并查看已连接账户与额度
适用场景
适合希望助手在无需本地模型和 GPU 的情况下处理音频或音乐的场景：转写会议与录音、清理与拆分音轨、制作旁白或克隆音色、按提示生成音乐。
运行要求
远程 Streamable-HTTP 端点 mcp.audiopod.ai（或仅含 9 个不生成新音频工具的 /core 端点），无需安装或本地运行时。首次使用需 OAuth 2.1 登录，无头或 CI 场景可改用 X-API-Key 请求头提供 AudioPod API 密钥。需要网络访问。
安装前请注意
提交的音频会由 AudioPod 托管服务处理。声音克隆需要获得同意，并会生成可复用的音色身份，请仅克隆你有权使用的声音。生成类工具会消耗账户额度，长时间任务需要轮询。请妥善保管 X-API-Key，避免写入共享配置。

安装

在 SourceWeft 中

  1. 打开 控制台中的 AudioPod AI，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 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。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/ai.audiopod%2Faudiopod/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "audiopod-ai": {
      "type": "http",
      "url": "https://mcp.audiopod.ai/"
    }
  }
}

README

AudioPod MCP Server

Hosted Model Context Protocol server for AudioPod's audio AI. Give any MCP-capable agent — Claude Desktop, Claude Code, Cursor, Continue, Cline, Goose, Codex — audio tools over a remote endpoint. No install, no local models, no GPU.

Full endpointhttps://mcp.audiopod.ai — 18 tools: transcription, stems, noise removal, speakers, MIDI, conversion, speech, voices and music
Core endpointhttps://mcp.audiopod.ai/core — 9 tools that work on audio you already have; none creates new audio
TransportStreamable-HTTP (MCP 2025-06-18)
AuthOAuth 2.1 — your client opens a sign-in window on first use. For CI / headless use, send X-API-Key: ap_* instead (get a free key)
Docshttps://docs.audiopod.ai/agents · MCP reference https://docs.audiopod.ai/sdks/mcp
Discovery/.well-known/mcp/server-card.json

Registry names (official MCP Registry): ai.audiopod/audiopod (full, server.json) and ai.audiopod/audiopod-core (core, server-core.json).

Installing with an agent? llms-install.md is the unattended-install guide — config for each client, how to verify, and the failures to expect.

Using a coding agent? AudiopodAI/audiopod-plugins wraps this server plus fourteen task skills as a one-command install for the major agent CLIs and editors.

Prefer HTTP? The same capabilities are a REST API, and the public Getting Started collection reaches a real 200 in two requests with no account and no API key. More about the collections.

[Run in Postman]

Tools

ToolEndpointDoes
transcribe_audiofull, coreTranscribe with word-level timestamps, speaker labels and SRT/VTT subtitles
separate_stemsfull, coreSplit a track into stems (vocals, drums, bass, …); two-stem mode = karaoke
denoise_audiofull, coreRemove background noise while preserving voice character
separate_speakersfull, corePut each speaker on their own track
convert_mediafull, coreConvert audio/video formats (mp3/wav/flac/ogg/m4a, mp4/mov)
audio_to_midifull, coreConvert a recording to MIDI
check_job_statusfull, corePoll the status/result of a long-running job (free)
get_accountfull, coreCheck account and credits
get_profilefull, coreIdentify the connected account
text_to_speechfullSpeech in 200+ languages, 500+ voices and custom clones
clone_voicefullClone a voice (200+ languages) from a 5–30s reference clip, with consent
change_voicefullConvert a recording to a different target voice
generate_musicfullSongs, instrumentals, rap, or vocal stems from a text prompt
compose_musicfullCompose a song score
revise_music_scorefullRevise a song score
record_music_scorefullRecord a song score to audio
get_music_scorefullRead a song score
edit_music_scorefullDeprecated alias of revise_music_score

Long-running tools return a job_id; poll with check_job_status.

Add it

Claude Code (OAuth sign-in on first use; swap in /core for the core endpoint)

bash
claude mcp add --transport http audiopod https://mcp.audiopod.ai --scope user

Claude Desktop / Cursor / Continue / Cline — add to your mcpServers config:

json
{  "mcpServers": {    "audiopod": { "url": "https://mcp.audiopod.ai" }  }}

Headless / CI — skip OAuth with an API key header:

json
{  "mcpServers": {    "audiopod": {      "url": "https://mcp.audiopod.ai",      "headers": { "X-API-Key": "ap_YOUR_KEY" }    }  }}

Try it (raw JSON-RPC)

bash
# List toolscurl -s https://mcp.audiopod.ai \  -H "X-API-Key: ap_YOUR_KEY" -H "Content-Type: application/json" \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
# Text to speechcurl -s https://mcp.audiopod.ai \  -H "X-API-Key: ap_YOUR_KEY" -H "Content-Type: application/json" \  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call",       "params":{"name":"text_to_speech","arguments":{"text":"Hello from my agent."}}}'

Building a startup on this?

Apply to AudioPod for Startups — free Pro for 3 months plus developer API credits for eligible early-stage teams.

Links

Three manifests live here and they are not interchangeable: server.json and server-core.json are the official registry entries (registry schema) for the full and core endpoints, server-card.json is the MCP server card — a reference copy, since the live card is served at the Discovery URL above.

License

MIT — see LICENSE. (Covers this listing/README; the AudioPod service itself is governed by the AudioPod Terms.)

来源：README.md，提交 549eaa6

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

2
  1. v2026.10.14最新Oct 14, 2026
  2. v2026.9.19Sep 19, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Audiopod 集成

AudioPod AI (core)

ai.audiopod官方发布者

托管的 AudioPod 音频 AI 服务器，让助手通过远程端点转写音频、分离音轨、降噪、区分说话人并转换为 MIDI。

Streamable HTTP可网页运行鉴权
媒体与设计需要凭据Nov 4, 2026