ElevenLabs

ElevenLabs provides highly realistic AI voices with advanced prosody and natural speech patterns, delivering lifelike audio synthesis with emotional nuance and conversational flow.

Paid plan required

You need a paid ElevenLabs plan for reliable TTS integration.

ElevenLabs may restrict or disable free-tier accounts due to abuse-detection mechanisms, even if free credits are available. To avoid missing audio responses during testing and production, ensure you use a paid plan.

The following example shows a starting tts parameter configuration you can use when you Start a conversational AI agent.

_10

"tts": {

_10

"vendor": "elevenlabs",

_10

"params": {

_10

"base_url": "wss://api.elevenlabs.io/v1",

_10

"key": "<your_elevenlabs_key>",

_10

"model_id": "eleven_flash_v2_5",

_10

"voice_id": "pNInz6obpgDQGcFmaJgB",

_10

"sample_rate": 24000

_10

}

_10

}

caution

The parameters listed on this page are validated for use with Conversational AI Engine. Required parameters must be provided as documented. Any additional parameters are passed through directly to the underlying vendor without validation. For advanced configuration options, voice cloning, and detailed parameter descriptions, see the ElevenLabs TTS documentation.

paramsrequired

• base_url stringrequired

  The endpoint URL for the OpenAI TTS service. See Data residency.

• key stringrequired

  The API key used for authentication. Get your API key from the ElevenLabs Console.

• model_id stringrequired

  Identifier of the model to be used. Popular options include eleven_flash_v2_5 for speed or eleven_multilingual_v2 for quality.

• voice_id stringrequired

  The identifier for the selected voice for speech synthesis. Browse available voices in the Voice Library.

• sample_rate numbernullable

  Default: 24000

  Audio sampling rate in Hz. Common values: 16000, 22050, 24000, 44100.

• speed numbernullable

  Default: 1.0

  Speed up or slow down the speed of the generated speech. Range 0.7 to 1.2 inclusive.

• stability numbernullable

  Controls voice stability. Higher values (0.8-1.0) produce more consistent speech, lower values (0.0-0.5) add more variation.

• similarity_boost numbernullable

  Enhances similarity to the original voice. Range: 0.0-1.0. Higher values stick closer to the training voice.

• style numbernullable

  Controls speaking style and expressiveness. Higher values increase emotional range and variation.

• use_speaker_boost booleannullable

  Improves voice quality and similarity when enabled. Recommended for most use cases.