Giggy Speech MCP

io.github.GRQDigitalCapitalv1.0.0更新於 Oct 8, 2026

Giggy speech tools for AI agents: discover voices and generate text-to-speech.

已驗證Streamable HTTP可網頁執行Media & Design

概覽

AI 產生的概覽

讓助理瀏覽 Giggy 語音並提交文字轉語音工作，再輪詢取得生成完成的音訊連結。

功能
這是一個遠端 Streamable HTTP MCP 伺服器，提供 Giggy 語音工具：list_voices 與 list_my_voices 用來探索可用的語音 ID，generate_speech 用來提交文字轉語音工作，get_speech_generation 用來查詢工作狀態。生成是非同步的：工具回傳持久化的中繼資料與生成 UUID，而不是即時音訊位元組，狀態變成 completed 後可從結果連結取得音訊。端點為無狀態，接受 POST 請求。
適用情境
當助理或程式開發代理需要透過 Giggy 把文字轉成語音時使用，例如為生成的內容配音，或把語音輸出接進代理工作流程。適合能輪詢工作直到完成的用戶端，而不是預期在工具回應中直接拿到音訊的情境。
執行需求
遠端 MCP 端點 Streamable HTTP，不需要本機套件或執行環境。需要 Giggy API 金鑰，以 Authorization bearer 權杖送出，通常在用戶端設定中透過 GIGGY_API_KEY 環境變數提供。需要連線至 giggy.ai 的網路。
安裝前請注意
Authorization bearer 權杖是機密金鑰，不要寫進提示詞、提交到版本控制或嵌入瀏覽器 JavaScript，也不要提交已設定的用戶端檔案。語音生成是 Giggy 的付費服務，使用可能產生費用。伺服器會提交生成工作並在帳號上寫入生成紀錄，每次新的生成應使用新的幂等鍵以避免重複。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Giggy Speech MCP，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

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

README

Giggy MCP — text-to-speech for AI agents

[MCP Docs CI]

Giggy MCP is a remote Streamable HTTP Model Context Protocol (MCP) server for using Giggy text-to-speech from coding agents and AI clients.

It provides Giggy speech tools to Codex, Claude Code, Cursor, VS Code, Cline, Windsurf-compatible clients, and other MCP clients.

MCP registry and plugin directories

Giggy's remote speech MCP endpoint is:

https://giggy.ai/mcp

This repository contains the publication artifacts for:

See directory submission status and requirements.

A public registry listing, plugin submission, and approved plugin publication are separate steps. Consult the submission document for verified status.

Quick setup

Use Giggy MCP with Codex

Set GIGGY_API_KEY in your environment, then add to ~/.codex/config.toml:

toml
[mcp_servers.giggy-speech]url = "https://giggy.ai/mcp"bearer_token_env_var = "GIGGY_API_KEY"

Use Giggy MCP with Claude Code

Set GIGGY_API_KEY, then configure:

json
{  "mcpServers": {    "giggy-speech": {      "type": "http",      "url": "https://giggy.ai/mcp",      "headers": { "Authorization": "Bearer ${GIGGY_API_KEY}" }    }  }}

Keep API keys out of configuration files committed to source control.

Remote MCP server

text
https://giggy.ai/mcp

Transport:

text
Streamable HTTP

The current Giggy MCP endpoint is stateless and accepts POST requests.

Authentication

Use a Giggy API key:

text
Authorization: Bearer $GIGGY_API_KEY

Giggy API keys begin with:

text
giggy_sk_

Keep the key in your MCP client's secret or environment configuration.

Do not:

  • put it in ordinary prompts
  • commit it to source control
  • embed it in browser JavaScript

Speech tools

This repository documents these Giggy speech tools:

text
list_voiceslist_my_voicesgenerate_speechget_speech_generation

The MCP server may expose other Giggy tools outside the speech scope of this repository.

Recommended speech workflow

  1. Call list_voices or list_my_voices.
  2. Select the exact returned voice_id.
  3. Call generate_speech.
  4. Supply a fresh idempotency_key for each new intended generation.
  5. Save generation.generation_uuid.
  6. Call get_speech_generation while the status is queued or processing.
  7. When the status becomes completed, use generation.result.url.

Do not resubmit a new generation while polling an existing generation.

Use Giggy MCP with Codex

Set:

bash
export GIGGY_API_KEY="giggy_sk_..."

Then add this to:

text
~/.codex/config.toml
toml
[mcp_servers.giggy-speech]url = "https://giggy.ai/mcp"bearer_token_env_var = "GIGGY_API_KEY"

A ready-to-copy version is included at:

text
examples/codex-config.toml

Verify:

bash
codex mcp list

Use Giggy MCP with Claude Code

Set:

bash
export GIGGY_API_KEY="giggy_sk_..."

A project MCP configuration is included at:

text
examples/claude-code.mcp.json

Its contents are:

json
{  "mcpServers": {    "giggy-speech": {      "type": "http",      "url": "https://giggy.ai/mcp",      "headers": {        "Authorization": "Bearer ${GIGGY_API_KEY}"      }    }  }}

Copy that configuration to:

text
.mcp.json

in the project where Claude Code should use Giggy.

Then run:

bash
claude mcp list

or use:

text
/mcp

inside Claude Code.

Other MCP clients

Ready-to-copy client configurations are included for:

ClientExample
Codexexamples/codex-config.toml
Claude Codeexamples/claude-code.mcp.json
Cursorexamples/cursor.mcp.json
VS Codeexamples/vscode.mcp.json
Clineexamples/cline.mcp.json
Windsurf-compatible clientsexamples/windsurf.mcp.json

Cursor

Set:

bash
export GIGGY_API_KEY="giggy_sk_..."

Copy or merge:

text
examples/cursor.mcp.json

into:

text
.cursor/mcp.json

for project configuration, or:

text
~/.cursor/mcp.json

for global configuration.

VS Code

Copy or merge:

text
examples/vscode.mcp.json

into:

text
.vscode/mcp.json

VS Code will prompt securely for the Giggy API key.

Cline

Open Cline's MCP server configuration and copy the contents of:

text
examples/cline.mcp.json

Replace:

text
YOUR_GIGGY_API_KEY

in your local configuration only.

Do not commit the configured file.

Windsurf-compatible clients

For installations that use:

text
~/.codeium/windsurf/mcp_config.json

merge the contents of:

text
examples/windsurf.mcp.json

and replace:

text
YOUR_GIGGY_API_KEY

in the local configuration only.

Raw MCP examples

Set:

bash
export GIGGY_API_KEY="giggy_sk_..."

Initialize:

bash
./examples/initialize.sh

List tools:

bash
./examples/list-tools.sh

List public voices:

bash
./examples/list-voices.sh

Important behavior

generate_speech returns durable generation metadata.

It does not return live MP3 or PCM audio bytes through MCP.

For progressive PCM audio, use:

text
POST https://giggy.ai/v1/text-to-speech

with:

text
mode=streamingoutput_format=pcm_24000

Developer resources

Speech API documentation:

text
https://giggy.ai/docs/speech-api

OpenAPI:

text
https://giggy.ai/v1/openapi.json

Runnable examples:

text
https://github.com/GRQDigitalCapital/giggy-examples

Pricing:

text
https://giggy.ai/pricing

Official SDK and runnable examples:

來源：README.md，提交 5f84f4e

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Oct 8, 2026