Teach the workflow once
A skill gives the LLM a repeatable way to turn text into tagged, template-backed speech instead of relying on a fresh explanation in every chat.
Text-to-speech skills
Text-to-speech skills that make LLM voice work easier
TextToSpeechSkills packages the speech workflow into reusable instructions and tools, so an LLM app knows how to prepare scripts, add natural expression directions, reuse voice templates, and create audio jobs without a long prompt every time.
Who is this for?
Text-to-speech skills are reusable instructions and helper workflows prepared to teach an LLM app how to create audio with TextToSpeechSkills after npm publication. The package source covers scripts, natural-language expression directions, saved voice templates, credit checks, MCP speech jobs, and audio links for review. Until release, users can follow the same content model in the studio or API.
Easy LLM setup
LLM-ready even for non-technical teams
Use the browser studio or API today. After the npm package is published, connect the MCP server, choose the skills workflow, and tell your LLM app which voice templates are allowed.
Read setup guide01Create a scoped key
02Use the studio or API
03Choose a voice template
04Generate and review audio
Keep prompt instructions consistent
The same rules for natural expression markup, templates, credit checks, and job creation can be reused across creators, teams, and workspaces.
Pair skills with MCP tools
After npm publication, skills will explain what good speech work looks like while MCP tools safely validate, preview, create, and retrieve audio.
When this helps
Creators, teams, and developers who want LLM apps to handle text-to-speech workflows usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are teach the workflow once, keep prompt instructions consistent, pair skills with mcp tools. 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 text-to-speech skills, text to speech skill, LLM TTS skills, AI speech workflow, 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 Text-to-Speech Skills for LLM Workflows?
Creators, teams, and developers who want LLM apps to handle text-to-speech workflows 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 today. After the npm package is published, connect the MCP server, choose the skills workflow, and tell your LLM app which voice templates are allowed. 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