TextToSpeechSkills
Start test plan

API for product teams

Text-to-speech API built for agent workflows

TextToSpeechSkills gives developers one practical workflow for turning app text into consistent speech: validate expression tags, choose a saved voice template, create a job, then poll or receive a webhook when audio is ready.

See LLM setupExplore product

Who is this for?

TextToSpeechSkills is a text-to-speech API for developers who need expressive speech in LLM apps, agents, and product workflows. It turns text into speech with readable expression tags, reusable voice templates, async generation jobs, scoped API keys, webhooks, MCP tools, and usage controls. Teams can start in the browser UI, then move the same workflow into code or an LLM app. This makes it useful for apps that need consistent narration, customer replies, educational audio, product updates, game dialogue, and automated voice output without exposing engine choices or secrets to end users.

Easy LLM setup

LLM-ready even for non-technical teams

LLM setup is a copy-and-paste flow: create a scoped key, copy the MCP command, paste it into your LLM app, and tell the agent which voice template to use.

Read setup guide
01Create a scoped key
02Install MCP
03Choose a voice template
04Generate audio from chat

Use readable expression tags

Product teams can write tone directly in the text, so prompts stay understandable during review and testing.

Keep voices consistent

Voice templates store persona, pacing, warmth, and stability settings so repeated prompts do not drift.

Build around jobs, not waiting

The API returns predictable job states for queued and fast paths, which keeps frontend clients clean and avoids leaking server credentials.

When this helps

Developers building agent workflows, product narration, and speech features usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are use readable expression tags, keep voices consistent, build around jobs, not waiting. 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 text-to-speech API, TTS API for developers, speech API for apps, 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 Text-to-Speech API for LLM Apps?

Developers building agent workflows, product narration, and speech features 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?

LLM setup is a copy-and-paste flow: create a scoped key, copy the MCP command, paste it into your LLM app, and tell the agent which voice template to use. 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.

Related reading

Keep exploring TextToSpeechSkills

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

LLM Text-to-Speech Setup GuideA simple guide for connecting TextToSpeechSkills to LLM apps with MCP, scoped keys, voice templates, and expression tags.Text-to-Speech MCP for LLM AppsConnect LLM apps to expressive text-to-speech with MCP tools for tags, voice templates, credit previews, jobs, and audio URLs.Text-to-Speech Skills for LLM WorkflowsInstall text-to-speech skills that teach LLM apps how to use expression tags, saved voices, MCP tools, and speech jobs safely.TTS MCP ServerInstall an MCP server that lets LLM agents validate expression markup, check credit use, use voice templates, and create speech jobs.How to Add Text-to-Speech to an LLM AppA practical launch guide for adding text-to-speech to LLM apps with expression tags, voice templates, MCP setup, jobs, and team billing.Expression Tags for Better AI Voice OutputLearn how expression tags make text-to-speech scripts easier to review, automate, and reuse across LLM apps, creators, games, and support flows.

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