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
LogoLogo
Login
Login
Connect
BlogHelp CenterAPI PricingSign up
ElevenAPIText to Speech

Multi-Context WebSocket

WSS
/v1/text-to-speech/:voice_id/multi-stream-input
Handshake
URLwss://api.elevenlabs.io/v1/text-to-speech/{voice_id}/multi-stream-input
MethodGET
Status101 Switching Protocols
Messages
The Multi-Context Text-to-Speech WebSockets API allows for generating audio from text input while managing multiple independent audio generation streams (contexts) over a single WebSocket connection. This is useful for scenarios requiring concurrent or interleaved audio generations, such as dynamic conversational AI applications. Each context, identified by a context id, maintains its own state. You can send text to specific contexts, flush them, or close them independently. A `close_socket` message can be used to terminate the entire connection gracefully. For more information on best practices for how to use this API, please see the [multi context websocket guide](/docs/eleven-api/guides/how-to/websockets/multi-context-web-socket).
Was this page helpful?
Previous

Create speech

Next
Built with

The Multi-Context Text-to-Speech WebSockets API allows for generating audio from text input while managing multiple independent audio generation streams (contexts) over a single WebSocket connection. This is useful for scenarios requiring concurrent or interleaved audio generations, such as dynamic conversational AI applications.

Each context, identified by a context id, maintains its own state. You can send text to specific contexts, flush them, or close them independently. A close_socket message can be used to terminate the entire connection gracefully.

For more information on best practices for how to use this API, please see the multi context websocket guide.

Handshake

WSS
/v1/text-to-speech/:voice_id/multi-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

initializeConnectionMultiobjectRequired

Message to initialize a new TTS context in a multi-context stream.

OR
initialiseContextobjectRequired

Message to initialize or re-initialize a TTS context with text and settings for multi-stream connections.

OR
sendTextMultiobjectRequired
Message to send text for synthesis to a specific context.
OR
flushContextClientobjectRequired
Message to flush the audio buffer for a specific context.
OR
closeContextClientobjectRequired
Message to close a specific TTS context.
OR
closeSocketClientobjectRequired
Message to gracefully close the entire WebSocket connection.
OR
keepContextAliveobjectRequired
Message to keep a specific context alive by resetting its inactivity timeout.

Receive

audioOutputMultiobjectRequired
Server message containing an audio chunk for a specific context.
OR
finalOutputMultiobjectRequired
Server message indicating the final output for a specific context.

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’.