Plain text stays plain
Bracketed directions sit inline with the sentence, so text remains easy to diff, approve, and store in prompts.
Readable audio direction
Expression markup your team can actually edit
Use natural-language bracketed directions to make generated speech match the moment. Writers can review the same text that developers send to the API, and agents can validate the markup before creating audio.
Who is this for?
Expressive TTS markup in TextToSpeechSkills is a simple way to add voice direction directly inside normal text. A writer, developer, or LLM agent can use natural-language cues such as [quiet], [excited but professional], or [loud and angry] to guide delivery while keeping the script readable. The same validation rules run in the UI, API, MCP server, and skills package, so unclear syntax can be caught before generation. This helps product teams keep copy reviewable, voice output consistent, and automated audio workflows easier to debug.
Easy LLM setup
LLM-ready even for non-technical teams
Agents use the same bracketed directions humans see in the editor, so a non-technical teammate can approve the exact words and performance notes before audio is created.
Read setup guide01Create a scoped key
02Install MCP
03Choose a voice template
04Generate audio from chat
Validation before generation
The API, UI, MCP server, and skill all use the same markup rules to catch unclear bracket syntax early.
Designed for repeatable style
Combine natural-language markup with templates to keep one product voice while changing emotion from line to line.
When this helps
Teams that want expressive voice direction without brittle prompt instructions usually need a repeatable path for writing, review, generation, billing, and reuse. The most important jobs here are plain text stays plain, validation before generation, designed for repeatable style. 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, API, or MCP. The same pattern works for expressive TTS, speech markup, natural expression markup, 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, 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 Expressive TTS Markup for Product Copy?
Teams that want expressive voice direction without brittle prompt instructions 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?
Agents use the same bracketed directions humans see in the editor, so a non-technical teammate can approve the exact words and performance notes before audio is created. 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 install
Agent tools included at launch
Claude Desktop
npx --yes --package texttospeechskills tts-skills-mcpCodex
npx --yes --package texttospeechskills tts-skills-mcpCursor
npx --yes --package texttospeechskills tts-skills-mcpSkills helper
npx --yes --package texttospeechskills tts-skills tagsThe public package includes the MCP server, skill instructions, SDK, CLI, OpenAPI file, resources, and prompts.