Who is this for?

Voice templates in TextToSpeechSkills are reusable settings for persona, tone, pace, warmth, stability, sample prompts, and style rules. They let teams separate the voice from the script, which means a developer or LLM agent can send text plus a template ID instead of repeating subjective voice instructions in every request. Templates are versioned so teams can test changes before making them active. This is especially useful for apps, channels, courses, and agents that need the same recognizable voice across many pieces of generated speech.

Easy LLM setup

LLM-ready even for non-technical teams

Give your LLM agent a template name instead of a pile of style instructions. It can reuse approved voices without changing your product settings.

Read setup guide

01Create a scoped key

02Install MCP

03Choose a voice template

04Generate audio from chat

Version every change

Test new delivery settings against sample prompts before promoting a template for production use.

Separate voice from content

Developers send text and a template ID instead of repeating style instructions in every request.

Ready for workspaces

Teams on Pro and higher can manage shared templates under central billing and scoped keys.

When this helps

Teams that need consistent voices across prompts, scripts, and products usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are version every change, separate voice from content, ready for workspaces. 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 expression tags when tone matters, choose an approved voice template, and create a speech job through the UI, API, or MCP. The same pattern works for voice templates, consistent text-to-speech voice, speech templates, which makes it easier for humans and LLM apps to share one process without exposing internal routing or credentials.

Before you roll it out

Decide which templates are approved, which expression tags are allowed, 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 Reusable Voice Templates for Text to Speech?

Teams that need consistent voices across prompts, scripts, and products 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 expression tags, voice templates, credit previews, and job-based generation.

Can a non-technical user connect this to an LLM app?

Give your LLM agent a template name instead of a pile of style instructions. It can reuse approved voices without changing your product settings. 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.

Keep exploring TextToSpeechSkills

Use these guides to move from a first audio test to a repeatable workflow for your team.

API playground

Plain JSON in, speech job out

{
  "text": "[quiet] hello. [loud and angry] how are you?",
  "voice_template": "vt_calm_narrator_v1",
  "generation_mode": "instant",
  "format": "mp3"
}

202 queued for polling200 audio ready

MCP install

Agent tools included at launch

Claude Desktoppnpm --package texttospeechskills dlx tts-skills-mcp

Codexpnpm --package texttospeechskills dlx tts-skills-mcp

Cursorpnpm --package texttospeechskills dlx tts-skills-mcp

Skills helperpnpm --package texttospeechskills dlx tts-skills tags

Create one voice once, then reuse it everywhere