ElevenLabs
Text-to-speech
ElevenLabs voices offer expressive, human-like pronunciation and an extensive list of supported languages. Every ElevenLabs voice can be used with all of the ElevenLabs models.
Models
Consult ElevenLabs’ documentation for an up-to-date list of available models and supported languages.
Voices
Only voices from SignalWire’s catalog below resolve on the platform. Voice IDs from your own ElevenLabs account — including custom or cloned voices — will not work by default. ElevenLabs voice import is available by request: see Custom and cloned voices for details.
Press play to audition any ElevenLabs voice, then copy config to grab the value for SWML or your SDK.
You can use the Name and ID values for each voice in the below table interchangeably.
Usage
ElevenLabs voice IDs conform to the following format:
Examples:
Languages
ElevenLabs’ multilingual models are designed to be interchangeably compatible with all supported languages.
Rather than enforcing language selection with language code,
this TTS model automatically uses the appropriate language of the input text.
Consult ElevenLabs’ supported languages resource for an up-to-date list of supported languages.
Examples
Learn how to use ElevenLabs voices on the SignalWire platform.
SWML
WebSocket (Relay)
Use the
languages
SWML method to set one or more voices for an AI agent.
Alternatively, use the say_voice parameter
of the play
SWML method to select a voice for basic TTS.
The Server SDKs build each document and serve it at /swml on port 3000.
The server answers only requests that carry the username signalwire and the password you set
in place of <YOUR_BASIC_AUTH_PASSWORD>. To send calls from your phone number to the server,
follow Answer a call via SWML.