For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
LogoLogo
Ask AIPlaygroundLoginFree API Key
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
  • Flux TTS
    • Overview
    • Voices & Languages
    • Batch vs Streaming: Which Should I Use?
    • Build a Flux TTS Voice Agent
    • Template Apps
    • Migrating from Aura to Flux TTS
  • Aura
    • Streaming (WebSocket)
      • Getting Started
      • Feature Overview
      • Template Apps
    • Batch (REST)
    • Voices & Languages
  • Voice Controls
    • Voice Controls
  • Media Output Settings
    • Encoding
    • Bit Rate
    • Container
    • Sample Rate
  • Results Processing
    • TTS Tagging
    • TTS Callback
    • Audio Output Streaming
  • Tips and Tricks
    • Real-Time TTS with WebSockets
    • Text Chunking for TTS
    • Formatting text for Aura-2
    • Handling Audio Issues in Text To Speech
    • Sending LLM Outputs to a WebSocket
    • Text Chunking for TTS REST Optimization
    • Text to Speech Latency
    • Text to Speech Prompting
    • TTS Troubleshooting WebSocket, NET, and DATA Errors
  • Overview
  • Getting Started
  • Feature Overview
  • Client Messages
  • Server Messages
  • The Speech Lifecycle
  • Cross-Turn Context
  • Getting Started
  • Voices & Languages
  • Batch vs Streaming: Which Should I Use?
  • Build a Flux TTS Voice Agent
  • Template Apps
  • Migrating from Aura to Flux TTS
  • Streaming (WebSocket)
  • Getting Started
  • Feature Overview
  • Template Apps
  • Flush
  • Clear
  • Close
  • Batch (REST)
  • Getting Started
  • Feature Overview
  • Template Apps
  • Voices & Languages
  • Voice Controls
  • Media Output Settings
  • Encoding
  • Bit Rate
  • Container
  • Sample Rate
  • TTS Tagging
  • TTS Callback
  • Audio Output Streaming
  • Real-Time TTS with WebSockets
  • Text Chunking for TTS
  • Formatting text for Aura-2
  • Handling Audio Issues in Text To Speech
  • Sending LLM Outputs to a WebSocket
  • Text Chunking for TTS REST Optimization
  • Text to Speech Latency
  • Text to Speech Prompting
  • TTS Troubleshooting WebSocket, NET, and DATA Errors
Ask AIPlaygroundLoginFree API Key
AuraStreaming (WebSocket)

Template Apps

Get up and running fast with our streaming text-to-speech template applications, fully integrated with Deepgram out-of-the-box.

Node.js
Node.js

Streaming text-to-speech demo app using Node.js

Bun
Bun

Streaming text-to-speech demo app using Bun

Deno
Deno

Streaming text-to-speech demo app using Deno

Flask
Flask

Streaming text-to-speech demo app using Flask

Django
Django

Streaming text-to-speech demo app using Django

FastAPI
FastAPI

Streaming text-to-speech demo app using FastAPI

Go
Go

Streaming text-to-speech demo app using Go

.NET
C# / .NET

Streaming text-to-speech demo app using C# / .NET

Java
Java

Streaming text-to-speech demo app using Java

Ruby
Ruby

Streaming text-to-speech demo app using Ruby

PHP
PHP

Streaming text-to-speech demo app using PHP

C++
C++

Streaming text-to-speech demo app using C++

Rust
Rust

Streaming text-to-speech demo app using Rust

Was this page helpful?
Previous

Flush

Flush forces the generation of audio from Deepgram's internal text buffer.
Next
Built with