text-to-speech
Provides text-to-speech synthesis using Google Translate's TTS endpoint, supporting multiple languages and accents.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@text-to-speech convert 'Hello, how are you?' to speech with a British accent"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Text-to-Speech MCP Server
An MCP server that exposes a text-to-speech
tool, powered by the free, no-API-key gTTS
library (which wraps Google Translate's internal TTS endpoint).
Free — no API key, no billing, no GCP account.
Many languages — English, Bengali, Spanish, and ~60 more.
File output — saves an MP3 and returns its path.
Resilient — retries transient/rate-limit failures with exponential backoff.
Note: gTTS uses an undocumented Google endpoint. It requires internet access and can rate-limit or change without notice — great for personal/internal use, less suited to high-volume production. The engine is isolated in
engine.pyso it can be swapped for Google Cloud TTS or an offline engine later.
Requirements
Python 3.12 (uv will provision it)
Related MCP server: TTS MCP Server
Setup
uv syncThis creates .venv/ and installs the project (and its deps: gtts, mcp).
Optional configuration — copy .env.example to .env and edit:
Variable | Default | Meaning |
|
| Where MP3s are written when no |
|
| Max synthesis attempts before failing |
|
| Base backoff seconds (1s, 2s, 4s, …) |
|
| Default language code |
|
| Default accent TLD |
Run
uv run tts-server
# or
uv run python -m tts_server.serverThe server speaks MCP over stdio.
Tools
text_to_speech
Arg | Type | Default | Description |
| string | — (required) | Text to speak |
| string |
| Language code ( |
| boolean |
| Speak more slowly |
| string |
| Accent TLD: |
| string | auto | Output MP3 path; auto-generated under |
Returns: Saved <N> KB MP3 to <path>, or Error: <reason>.
list_languages
No arguments. Returns supported code: name pairs.
Install in an MCP client
This is a standard stdio MCP server, so it works with any MCP-compatible client (Claude Code, Claude Desktop, Cursor, Windsurf, Continue, etc.). Every client needs the same three things:
Field | Value |
command |
|
args |
|
env (optional) | e.g. |
Replace <ABS_PROJECT_PATH> with the absolute path to this project. Using
uv --directory <path> run means the client can launch the server from anywhere
and still resolve the right virtual env and .env. Make sure uv
is on the client's PATH (or use the absolute path to the uv binary — find it
with which uv).
Claude Code (CLI)
# user scope = available in every project; use --scope project for just this repo
claude mcp add text-to-speech --scope user -- \
uv --directory /abs/path/to/text-to-speech-agent run tts-serverVerify, inspect, or remove:
claude mcp list # health check
claude mcp get text-to-speech # show config
claude mcp remove text-to-speechTools load when a session starts, so open a new session after adding.
Claude Desktop
Edit the config file (Settings → Developer → Edit Config, or directly):
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add (see claude_desktop_config.example.json):
{
"mcpServers": {
"text-to-speech": {
"command": "uv",
"args": ["--directory", "/abs/path/to/text-to-speech-agent", "run", "tts-server"],
"env": { "TTS_OUTPUT_DIR": "/abs/path/to/text-to-speech-agent/output" }
}
}
}Then fully restart Claude Desktop.
Cursor / Windsurf / other JSON-config clients
These use the same mcpServers JSON shape as Claude Desktop. Add the block above
to the client's MCP config (e.g. Cursor: Settings → MCP, or ~/.cursor/mcp.json),
then reload the client.
Generic stdio client
Any client that can launch a stdio server: configure it to run
uv --directory /abs/path/to/text-to-speech-agent run tts-serverand (optionally) pass environment variables from the table in Setup.
Troubleshooting
Server fails to start / "uv not found" — use the absolute path to
uv(which uv) as thecommand, since GUI clients often don't inherit your shellPATH.Tools don't appear — restart the client (Claude Code: start a new session).
MP3s land in the wrong place — set
TTS_OUTPUT_DIRin the client'senvblock (it overrides.env).Synthesis errors — gTTS needs internet and may rate-limit; the server retries automatically, but check connectivity if it persists.
Project layout
src/tts_server/
server.py # MCP tools, validation, response shaping
engine.py # gTTS wrapper + retry/backoff (only file importing gTTS)
config.py # env-driven settings
utils.py # filename gen, language validation, file sizing
tests/ # unit tests (retry paths, mocked gTTS)
output/ # generated MP3sTests
uv run python -m pytest -qAvailable Tools
2 toolslist_languagesA
List the language codes and names supported for text_to_speech.
Inputs: no named parameters. Returns: result
text_to_speechA
Convert text into spoken audio (MP3) using Google TTS (gTTS).
Args:
text: The text to speak. Required, must be non-empty.
language: Language code such as "en", "bn", "es". Defaults to "en".
slow: Speak more slowly when True.
accent: Google domain TLD controlling accent for some languages,
e.g. "com" (US), "co.uk" (UK), "com.au" (AU), "co.in" (India).
output_path: Where to write the MP3. If omitted, a timestamped file
is created under the configured output directory.
Returns:
A human-readable status string including the saved file path, or an
"Error: ..." message describing what went wrong.
Inputs: text (required), slow, accent, language, +1 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one lists supported languages, and the other converts text to speech. There is no overlap or ambiguity.
Both tools follow a consistent verb_noun pattern (list_languages, text_to_speech), making the naming predictable and intuitive.
With only two tools, the server is quite thin but still covers the core functionality for a simple text-to-speech service. The count is borderline for the domain.
The domain is well-covered by listing languages and converting text to speech with various options. No major gaps are apparent, though additional settings tools could be added.
Maintenance
Related MCP Connectors
Text to speech in 149 languages: MP3 links from any assistant. Free without an account.
Turn text into natural-sounding MP3 voice-overs in 6 languages. Free plan included.
Read text aloud in 48 languages, transcribe audio, extract and translate PDF text, dub video.
Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables text-to-speech conversion with smart language detection (using Google TTS for Chinese) and audio file playback with playback controls for Claude Desktop.2MIT
- AlicenseNot gradedqualityDmaintenanceProvides Text-to-Speech (TTS) functionality using Google TTS API, enabling audio generation, voice listing, and style templates via MCP.1MIT
- AlicenseAqualityDmaintenanceProvides text-to-speech synthesis using Microsoft Edge's free TTS engine, supporting multiple voices, languages, and audio output options (base64 or file).3MIT
- AlicenseNot gradedqualityCmaintenanceEnables converting text to speech audio in 20+ languages, returning base64-encoded MP3 output via Google TTS with x402 micropayment-based pay-per-call access.MIT