TTS Functional Overview & API Integration
Capacity Private Cloud TTS converts text into natural-sounding speech, with SSML markup for fine control over pronunciation, pacing, and voice. This page is a starting point: it routes you to the product overview, the supporting reference articles, and the developer API definitions.
Start here — TTS overview
Speech Products: TTS — what the text-to-speech product does, the available voices, and the capabilities it exposes.
Functional Overview & Background
These reference articles cover SSML — the markup that controls how text is spoken — and the synthesizer API. They are the foundation for producing speech that sounds the way your application intends.
| Article | What it covers |
| An Introduction to SSML | What Speech Synthesis Markup Language is and how it shapes synthesized speech. |
| SSML Elements | The individual SSML elements — voice, prosody, say-as, breaks, and more — and how to use them. |
| TTS Text Normalization | How the engine expands numbers, dates, currency, and other written forms into spoken words. |
| Synthesizer Methods | The synthesizer API methods for requesting and controlling speech output. |
Developer API Reference
The TTS developer references are published on the developer portal (developer.lumenvox.com) and remain the system of record. Use these when implementing directly against the gRPC API, configuring synthesis, or wiring up reporting.
| Reference | Description |
| TTS functional overview | Functional overview of TTS on the developer portal. |
| TTS integration | API integration guide for TTS. |
tts-lumenvox.proto | gRPC API definition for TTS interactions. |
| TTS configuration | Configuration settings for synthesis. |
reporting.proto | gRPC API definition for usage and results reporting. |