$ loading_
Convert text into lifelike speech with customizable voice, rate, volume, and pitch.
This tool appears narrowly scoped, requires no secrets in the provided materials, and is open source for review, with no clear high-risk red flags. The main cautions are that it runs locally as an MCP server and likely sends user text to Microsoft's Edge TTS online service, while the exact egress endpoints are not clearly documented.
The materials state that no keys or environment variables are required, and there is no indication that API tokens, account credentials, or other sensitive authentication data are needed, so credential exposure and abuse risk appears low.
Although no remote host is listed in the metadata, the description explicitly says it uses Microsoft Edge's Text-to-Speech service, which typically implies that user-provided text is sent to a Microsoft-operated online service. The likely recipient is inferable, but the exact domains, transmitted fields, and retention details are not disclosed in the materials.
The system checks indicate it executes code; as an MCP tool, it will at least run a local server process and handle text-to-speech requests. This is a normal capability for this class of tool, and the provided materials do not show any extra high-risk system privileges or execution behavior that is clearly inconsistent with its stated purpose.
Based on the available description, it primarily handles user-provided text and generated audio output, with no stated need for broad access to local files, system directories, browser data, or other data beyond what its function requires.
The project is open source under the MIT License and available in a public repository, which improves auditability, and it is listed in a third-party registry, both of which lower risk. However, it has 0 stars, unknown maintenance status, and no README content provided here, so maturity and ongoing maintenance are not well evidenced and dependencies/version provenance still warrant caution.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Edge TTS MCP" yet — see the docs or source repo.
Convert the following product introduction into speech using a Chinese female voice, with a slightly faster rate, normal volume, and slightly higher pitch. Return a playable audio result: Welcome to our smart scheduling assistant. It automatically organizes meeting times and sends reminders.
A playable product introduction audio clip with natural speech and the requested settings.
Convert this text into clear, slow American English speech suitable for learners to shadow, while keeping natural pauses: Artificial intelligence is changing how people work, learn, and communicate every day.
A slow, clear narration audio clip for English learning, with natural pronunciation and pauses.
Convert the following three notices into separate speech files using a formal male voice, normal rate, and slightly higher volume. Label outputs by notice title: 1. System Maintenance Notice: Maintenance starts at 10 PM tonight. 2. Meeting Reminder: Weekly meeting begins at 9 AM tomorrow. 3. Delivery Reminder: Your package has arrived at the front desk.
Three announcement audio files labeled by title, ready for playback or automation workflows.
Convert text to speech via one interface with local and cloud engines.
Access text-to-speech, speech-to-text, and voice management via ElevenLabs API.
Convert text into speech with Google TTS, voices, and style templates.
Build voice profiles from samples, then rewrite or generate text in that voice.
Convert speech into text for note-taking, organization, and analysis.
Adds speech recognition and text-to-speech for converting audio and text.