Use natural expression markup
Product teams can write full delivery directions directly in brackets, so prompts stay understandable during review and testing.
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: write natural-language expression directions, choose a saved voice template, create a job, then poll or receive a webhook when audio is ready.
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 today with natural-language bracketed expression directions, reusable voice templates, async generation jobs, scoped API keys, webhooks, and usage controls. Teams can start in the browser UI, then move the same workflow into code; scoped MCP tools follow after npm publication. 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
Teams can use the browser studio or API now. Copy-and-paste MCP setup will be enabled after the npm package is published, with scoped keys and approved voice templates.
Read setup guide01Create a scoped key
02Use the studio or API
03Choose a voice template
04Generate and review audio
Price API usage with the same credits
The same paid plan credits cover studio and API usage today, plus MCP usage after the package release, with credit previews before speech jobs run.
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, which keeps frontend clients clean and avoids leaking server credentials.
Pair with speech-to-text when agents listen
TextToSpeechSkills handles speech output from approved text. If an agent also receives user audio, pair it with a speech-to-text layer and send the response text here for voice output.
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 natural expression markup, price api usage with the same credits, keep voices consistent, build around jobs, not waiting, pair with speech-to-text when agents listen. 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 API, TTS API for developers, speech API for apps, 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 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 natural expression markup, voice templates, credit previews, and job-based generation.
Can a non-technical user connect this to an LLM app?
Teams can use the browser studio or API now. Copy-and-paste MCP setup will be enabled after the npm package is published, with scoped keys and approved voice templates. 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