Deepgram Text-To-Speech API
The Deepgram Text-to-Speech API converts text into natural-sounding speech using the Aura model family. It supports both single text requests and continuous streaming text-to-speech, delivering sub-200 millisecond latency suitable for real-time voice agents and conversational AI applications. The API offers multiple voice options and is designed for enterprise-grade deployments including voicebots, IVR systems, and interactive voice applications.
Documentation
Specifications
OpenAPI
openapi/deepgram-text-to-speech-openapi.yml
AsyncAPI
asyncapi/deepgram-text-to-speech-asyncapi.yml
Other Resources
Rules
rules/deepgram-text-to-speech-api-rules.yml
Capabilities
capabilities/deepgram-text-to-speech-api-capabilities.yml
OpenAPI
#Audio
#Speech Synthesis
#Text-To-Speech
#Voice