For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Connect
BlogHelp CenterAPI PricingSign up
OverviewElevenCreativeElevenAgentsElevenAPIAPI referenceChangelog
OverviewElevenCreativeElevenAgentsElevenAPIAPI referenceChangelog
  • API reference
    • Introduction
    • Authentication
    • Streaming
  • ElevenAgents
  • ElevenAPI
      • WSSWebSocket
      • WSSMulti-Context WebSocket
      • POSTCreate speech
      • POSTCreate speech with timing
      • STREAMStream speech
      • STREAMStream speech with timing
  • ElevenCreative
  • Core Resources
  • Workspace
  • Legacy
  • Conversational AI
LogoLogo
Login
Login
Connect
BlogHelp CenterAPI PricingSign up
ElevenAPIText to Speech

WebSocket

WSS
/v1/text-to-speech/:voice_id/stream-input
Handshake
URLwss://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream-input
MethodGET
Status101 Switching Protocols
Messages
The Text-to-Speech WebSockets API is designed to generate audio from partial text input while ensuring consistency throughout the generated audio. Although highly flexible, the WebSockets API isn't a one-size-fits-all solution. It's well-suited for scenarios where: * The input text is being streamed or generated in chunks. * Word-to-audio alignment information is required. However, it may not be the best choice when: * The entire input text is available upfront. Given that the generations are partial, some buffering is involved, which could potentially result in slightly higher latency compared to a standard HTTP request. * You want to quickly experiment or prototype. Working with WebSockets can be harder and more complex than using a standard HTTP API, which might slow down rapid development and testing.
Was this page helpful?
Previous

Multi-Context WebSocket

Next
Built with

The Text-to-Speech WebSockets API is designed to generate audio from partial text input while ensuring consistency throughout the generated audio. Although highly flexible, the WebSockets API isn’t a one-size-fits-all solution. It’s well-suited for scenarios where:

  • The input text is being streamed or generated in chunks.
  • Word-to-audio alignment information is required.

However, it may not be the best choice when:

  • The entire input text is available upfront. Given that the generations are partial, some buffering is involved, which could potentially result in slightly higher latency compared to a standard HTTP request.
  • You want to quickly experiment or prototype. Working with WebSockets can be harder and more complex than using a standard HTTP API, which might slow down rapid development and testing.

Handshake

WSS
/v1/text-to-speech/:voice_id/stream-input

Headers

xi-api-keystringOptional

Path parameters

voice_idstringRequired
The unique identifier for the voice to use in the TTS process.

Query parameters

authorizationstringOptional
Your authorization bearer token.
single_use_tokenstringOptional

Your single use token. Use this if you want to initiate a session from the client. When providing this parameter, xi-api-key is no longer required for authentication.

model_idstringOptional
The model ID to use.
language_codestringOptional

The ISO 639-1 language code (for specific models).

enable_loggingbooleanOptionalDefaults to true
Whether to enable logging of the request.
enable_ssml_parsingbooleanOptionalDefaults to false
Whether to enable SSML parsing.
output_formatenumOptionalDefaults to pcm_22050
The output audio format
inactivity_timeoutintegerOptionalDefaults to 20

Timeout for inactivity before a context is closed (seconds), can be up to 180 seconds.

sync_alignmentbooleanOptionalDefaults to false
Whether to include timing data with every audio chunk.
auto_modebooleanOptionalDefaults to false

Reduces latency by disabling chunk schedule and buffers. Recommended for full sentences/phrases.

apply_text_normalizationenumOptionalDefaults to off
This parameter controls text normalization with three modes - 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. For the 'eleven_flash_v2_5' model, text normalization can only be enabled with Enterprise plans. Defaults to 'auto'.
Allowed values:
seedintegerOptional0-4294967295

If specified, system will best-effort sample deterministically. Integer between 0 and 4294967295.

Send

initializeConnectionobjectRequired
OR
sendTextobjectRequired
OR
closeConnectionobjectRequired

Receive

audioOutputobjectRequired
OR
finalOutputobjectRequired

This parameter controls text normalization with three modes - ‘auto’, ‘on’, and ‘off’. When set to ‘auto’, the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With ‘on’, text normalization will always be applied, while with ‘off’, it will be skipped. For the ‘eleven_flash_v2_5’ model, text normalization can only be enabled with Enterprise plans. Defaults to ‘auto’.