Reusable instructor voices
Keep one recognizable instructor style across lessons, quizzes, walkthroughs, and updates.
For learning products
Use TextToSpeechSkills to create consistent educational audio for modules, onboarding paths, product academies, and internal training. Templates keep the instructor voice steady while natural expression markup adds emphasis where learners need it.
TextToSpeechSkills helps learning teams create narration for lessons, training modules, product academies, onboarding paths, and accessibility audio. A course can keep one instructor voice through reusable templates, while natural-language bracket directions add emphasis and pacing where learners need it. Course builders can use the studio or API today; after npm publication, MCP will let an LLM adapt lesson text, validate markup, and generate audio with the same templates and job model.
Easy LLM setup
Course builders can use an LLM to adapt lesson text, then validate and generate through the studio or API today. The MCP workflow follows after npm publication.
Read setup guideKeep one recognizable instructor style across lessons, quizzes, walkthroughs, and updates.
Natural expression markup adds audio direction without making source material difficult to edit.
Generate audio versions of learning content and store usage records for operations teams.
Course creators, learning platforms, internal training teams, and product educators usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are reusable instructor voices, readable lesson scripts, accessible by default. Those are the moments where voice becomes part of real work instead of a one-off export.
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 e-learning text-to-speech, course narration TTS, training audio API, helping humans and LLM apps share one process without exposing internal routing or credentials.
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
These are the practical details that matter before a team adds speech generation to a real workflow.
Course creators, learning platforms, internal training teams, and product educators 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.
Course builders can use an LLM to adapt lesson text, then validate and generate through the studio or API today. The 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.
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
{
"text": "[quiet] hello. [loud and angry] how are you?",
"voice_template": "vt_calm_narrator_v1",
"format": "wav"
}MCP package
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