NPC dialogue and barks
Give each character a saved template and use natural-language bracket cues for urgency, fear, confidence, or surprise.
For game creators
Create game voices without building an audio pipeline
Use TextToSpeechSkills for prototypes, indie games, internal playtests, and live content systems that need expressive speech. Save character voices as templates, add emotion with natural-language inline directions, and generate audio through the UI or API today; LLM app automation follows after npm publication.
Who is this for?
TextToSpeechSkills helps game creators generate voice lines for NPC dialogue, tutorials, mission updates, prototype scripts, and dynamic character barks. Each character can use a reusable voice template, while natural expression markup adds emotion and delivery notes such as [panicked but trying to stay quiet], [confident and teasing], or [urgent, shouting over battle noise]. Creators can use the studio or API today; after npm publication, the MCP workflow will let an LLM draft lines, validate markup, check credit use, and create speech jobs without changing the content model.
Easy LLM setup
LLM-ready even for non-technical teams
Use an LLM to draft NPC lines, then validate markup, select a character template, check credit use, and create audio through the studio or API. MCP automation follows after npm publication.
Read setup guide01Create a scoped key
02Use the studio or API
03Choose a voice template
04Generate and review audio
Tutorials and mission updates
Turn onboarding steps, quest text, and live event updates into consistent narration without recording sessions.
Prototype faster with agents
Use an LLM for draft lines and the studio or API for speech assets today; the unified MCP workflow follows after npm publication.
When this helps
Game creators, indie teams, modders, and interactive fiction builders usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are npc dialogue and barks, tutorials and mission updates, prototype faster with agents. 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 for games, NPC voice generator, game narration TTS, 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 Games and Interactive Characters?
Game creators, indie teams, modders, and interactive fiction builders 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 draft NPC lines, then validate markup, select a character template, check credit use, and create audio through the studio or API. MCP automation 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.
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