Create a scoped key
Use a workspace key for the LLM app so billing, permissions, and rotation are easy to manage.
Guide
LLM text-to-speech setup guide
This guide shows the available path from account to generated speech: create a scoped key, use the browser studio or API, pick a voice template, and generate audio with natural-language expression directions while the MCP package release is pending.
What does this guide cover?
The LLM text-to-speech setup guide explains the staged path to an agent workflow. Teams can choose a paid plan, create a scoped workspace key, test scripts in the browser studio, or call the API from a trusted backend today. After the npm package is published, the guide will add runnable MCP install commands for approved voice templates, expression validation, credit previews, speech jobs, and audio URLs. Billing and credentials remain controlled throughout the workflow.
Easy LLM setup
Connect an LLM app without building an integration first
You do not need to build an integration first. Use the browser studio for initial tests or the API for product work. MCP install commands will be published here after the npm package release.
Start test plan01Create a scoped workspace key.
02Use the browser studio or API while the MCP package release is pending.
03Pick approved voice templates for the agent.
04Generate tagged speech and review the audio job.
Use available interfaces first
Use the browser studio for manual tests or the API from a trusted backend. MCP commands will be enabled only after the npm package is published.
Use templates and expression markup
Tell the agent which voice template to use and let it add natural directions like [quiet], [excited but restrained], or [loud and angry].
Choose what belongs in the template
Keep persona, default pace, and durable delivery rules in the voice template. Keep scene-specific emotion in the script so a reviewer can approve exactly what changes.
Define the MCP handoff
Document the API workflow first: validate text, choose a template, estimate credits, create a job, and retrieve its audio. The prepared MCP tools will expose those same bounded steps after publication.
When this helps
Non-technical users and teams setting up speech generation inside LLM apps usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are create a scoped key, use available interfaces first, use templates and expression markup, choose what belongs in the template, define the mcp handoff. 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 LLM text-to-speech setup, MCP TTS guide, connect text-to-speech to LLM, 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 LLM Text-to-Speech Setup Guide?
Non-technical users and teams setting up speech generation inside LLM apps 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?
You do not need to build an integration first. Use the browser studio for initial tests or the API for product work. MCP install commands will be published here after the npm package release. 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