TextToSpeechSkills
Log inSign up

For video creators

Narrate YouTube videos from scripts, outlines, and agent drafts

Create consistent narration for explainers, tutorials, faceless channels, product videos, and Shorts. Keep a stable channel voice with templates, then use natural expression directions to make hooks, transitions, and calls to action sound intentional.

See LLM setupExplore product

Who is this for?

TextToSpeechSkills helps creators turn YouTube scripts, outlines, and LLM drafts into consistent narration. A channel can save its narrator as a voice template, then use natural-language expression markup to control hooks, transitions, emphasis, and calls to action. Creators can generate narration from the UI or batch longer scripts through the API today; MCP writing-workflow integration follows after npm publication.

Easy LLM setup

LLM-ready even for non-technical teams

Use an LLM to prepare the script, then generate narration through the studio or API today. The in-client MCP workflow follows after npm publication.

Read setup guide
01Create a scoped key
02Use the studio or API
03Choose a voice template
04Generate and review audio

Consistent channel voice

Save your narrator once and reuse the same voice template across intros, explainers, product demos, and series episodes.

Script markup that stays readable

Use bracketed directions for pacing and emphasis while keeping the script clean enough for editors and collaborators.

Batch-friendly audio jobs

Generate voiceovers from longer scripts with polling, webhooks, and clear credit previews before production.

When this helps

YouTube creators, video editors, faceless channels, and product marketers usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are consistent channel voice, script markup that stays readable, batch-friendly audio jobs. 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 YouTube narration text-to-speech, TTS for video narration, AI voiceover API, 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 for YouTube Narration?

YouTube creators, video editors, faceless channels, and product marketers 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 an LLM to prepare the script, then generate narration through the studio or API today. The in-client MCP workflow follows after npm publication. 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 staged guide for using TextToSpeechSkills now through the studio or API and connecting LLM apps through MCP after npm publication.Text-to-Speech MCP for LLM AppsLearn how TextToSpeechSkills is preparing MCP tools, prompts, expression markup, voice templates, credit previews, jobs, and audio URLs for LLM apps.Text-to-Speech Skills for LLM WorkflowsLearn how release-prepared text-to-speech skills will teach LLM apps to use natural-language expression markup, saved voices, MCP tools, and speech jobs safely.TTS MCP Server for Text-to-Speech AgentsReview the MCP server prepared for LLM agents to validate markup, check credits, use voice templates, and create speech jobs after npm publication.How to Add Text-to-Speech to an LLM AppAdd text-to-speech to LLM apps with expression markup, voice templates, API jobs, team billing, and MCP after npm publication.Natural Expression Markup for Better AI Voice OutputLearn how natural expression markup makes text-to-speech scripts easier to review, automate, and reuse across LLM apps, creators, games, and support flows.Voice Templates for Consistent AI SpeechA guide to reusable voice templates for consistent narrators, characters, support voices, course instructors, and LLM-generated speech.

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 yet

The 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