Small tool surface
After npm publication, agents will get focused speech tools instead of broad account access, making reviews and permissions easier.
MCP for speech generation
Give LLM agents a safe text-to-speech tool
The TextToSpeechSkills MCP server is prepared to let agents create speech without guessing your billing rules or voice settings after npm publication. Its narrow surface will validate markup, read speech resources, use prompts, pick approved templates, preview credit use, create jobs, and return audio URLs.
Who is this for?
The TextToSpeechSkills MCP server is prepared to give LLM apps a controlled way to create speech after npm publication. Its focused workflow validates natural expression markup, lists approved voice templates, reads resources, uses prompts, previews credit use, creates speech jobs, and retrieves audio URLs. Teams can use the studio or API now, then add the MCP command and allowed templates after release. Billing controls and keys remain separate from the prompt.
Easy LLM setup
LLM-ready even for non-technical teams
Use the browser studio or API now. The copyable MCP command and agent tools will become available after the npm package is published, while keys and billing controls stay scoped.
Read setup guide01Create a scoped key
02Use the studio or API
03Choose a voice template
04Generate and review audio
Templates over prompts
Approved templates keep brand voices steady while still letting agents add local natural expression cues.
Credit-aware generation
Usage previews and workspace permissions help teams keep automated audio generation under control.
Prepare the workflow before MCP release
Use the LLM setup guide to establish scoped keys, approved templates, markup rules, and API jobs now, then add the MCP command only after the package is published.
When this helps
People connecting LLM apps to speech generation with MCP usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are small tool surface, templates over prompts, credit-aware generation, prepare the workflow before mcp release. Those are the moments where voice becomes part of real work instead of a one-off export.
How the workflow works
Start with readable text, add natural-language expression directions when tone matters, choose an approved voice template, and create a speech job through the UI or API. After npm publication, MCP will use the same pattern for TTS MCP server, MCP voice tools, LLM text-to-speech, helping humans and LLM apps share one process without exposing internal routing or credentials.
Before you roll it out
Decide which templates are approved, how natural expression markup should be reviewed, who can create workspace keys, and which usage limits are acceptable. Those choices keep automated voice generation useful without letting it sprawl from the first paid Test plan through Pro, Scale, and Business usage.
Common questions
What teams usually ask before starting
These are the practical details that matter before a team adds speech generation to a real workflow.
Who should use TTS MCP Server for Text-to-Speech Agents?
People connecting LLM apps to speech generation with MCP should use this page when they want generated speech that is easy to review, consistent across prompts, and simple to connect to LLM tools. The core workflow combines natural expression markup, voice templates, credit previews, and job-based generation.
Can a non-technical user connect this to an LLM app?
Use the browser studio or API now. The copyable MCP command and agent tools will become available after the npm package is published, while keys and billing controls stay scoped. The setup guide keeps the first path short while still giving developers a clean API when the workflow moves into a product backend.
How does pricing stay predictable?
Every paid plan uses credits. Teams can add credit packs when needed, and workspaces on Pro and higher add central billing for $2 per user per month.
API playground
Plain JSON in, speech job out
{
"text": "[quiet] hello. [loud and angry] how are you?",
"voice_template": "vt_calm_narrator_v1",
"format": "wav"
}Job created200 audio ready
MCP package
MCP package release pending
npm release status
Install commands are not available yetThe package is prepared for release but is not published. Use the browser studio or API today; MCP commands will appear here after npm publication.
Read API docs