TTS Models

An overview of Text-to-Speech providers and models you can use with the Voice Agent API.

By default Deepgram Text-to-Speech will be used with the Voice Agent API. You can also use Deepgram’s native Cartesia support or opt to use another provider’s TTS model with your Agent by applying the following settings.

You can set your Text-to-Speech model in the Settings Message for your Voice Agent. See the docs for more information.

Deepgram TTS models

For a complete list of Deepgram TTS models see TTS Voice Selection.

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `deepgram`
`agent.speak.provider.model`	String	The TTS model to use
`agent.speak.provider.speed`	Float	Speaking rate multiplier. Range: `0.7` - `1.5`. Defaults to `1.0`. See TTS voice controls for details.

The Deepgram TTS speed parameter is in Early Access. To request access, contact your Account Executive or reach out to sales@deepgram.com.

Example

JSON

1 {
2   "speak": {
3     "provider": {
4       "type": "deepgram",
5       "model": "aura-2-thalia-en",
6       "speed": 0.9
7     }
8   }
9 }

Deepgram-managed Cartesia TTS models

Deepgram also provides managed support for Cartesia TTS. For a complete list of Cartesia TTS models, visit Cartesia’s TTS Docs. Cartesia is included in the Standard pricing tier.

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `cartesia`
`agent.speak.provider.model`	String	The TTS model to use
`agent.speak.provider.speed`	String or Number	Speaking rate control. Accepts `slowest`, `slow`, `normal`, `fast`, `fastest`, or a numerical value for more granular control. See Cartesia speed documentation.

Example

JSON

1 {
2 "agent": {
3   "speak": {
4     "provider": {
5       "type": "cartesia",
6       "model_id": "sonic-2",
7       "voice": {
8         "mode": "id",
9         "id": "a167e0f3-df7e-4d52-a9c3-f949145efdab"
10       },
11       "speed": "normal"
12     }
13   }
14 }
15 }

BYO Third Party TTS models

To use a third party TTS voice, specify the TTS provider and required parameters.

OpenAI

For OpenAI you can refer to this article on how to find your voice ID.

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `open_ai`
`agent.speak.provider.model`	String	The TTS model to use
`agent.speak.provider.voice`	String	The voice to use
`agent.speak.endpoint`	Object	Required and must include url and headers
`agent.speak.endpoint.url`	String	Your OpenAI API endpoint URL
`agent.speak.endpoint.headers`	Object	Required headers for authentication

Example

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "open_ai",
6         "model": "tts-1",
7         "voice": "alloy"
8       },
9       "endpoint": {
10         "url": "https://api.openai.com/v1/audio/speech",
11         "headers": {
12           "authorization": "Bearer {{OPENAI_API_KEY}}"
13         }
14       }
15     }
16   }
17 }

Eleven Labs

For ElevenLabs you can refer to this article on how to find your Voice ID or use their API to retrieve it. See their TTS Docs for more information. ElevenLabs does not support WebSocket streaming for the eleven_v3 model - instead, use the HTTPS REST endpoint (see example).

We support any of ElevenLabs’ Turbo 2.5 voices to ensure low latency interactions

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `eleven_labs`
`agent.speak.provider.model_id`	String	The model ID to use
`agent.speak.provider.language_code`	String	Optional Language code
`agent.speak.endpoint`	Object	Must include url and headers
`agent.speak.endpoint.url`	String	Your Eleven Labs API endpoint URL
`agent.speak.endpoint.headers`	Object	Headers for authentication

Example

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "eleven_labs",
6         "model_id": "eleven_turbo_v2_5",
7         "language_code": "en-US"
8       },
9       "endpoint": {
10         "url": "wss://api.elevenlabs.io/v1/text-to-speech/{voice_id}/multi-stream-input",
11         "headers": {
12           "xi-api-key": "{{ELEVEN_LABS_API_KEY}}"
13         }
14       }
15     }
16   }
17 }

Example (eleven_v3 via HTTPS)

Because eleven_v3 does not support WebSocket streaming, use the HTTPS REST endpoint:

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "eleven_labs",
6         "model_id": "eleven_v3",
7         "language_code": "en-US"
8       },
9       "endpoint": {
10         "url": "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}",
11         "headers": {
12           "xi-api-key": "{{ELEVEN_LABS_API_KEY}}"
13         }
14       }
15     }
16   }
17 }

Cartesia

For Cartesia you can use their API to retrieve a voice ID. See their TTS API Docs for more information.

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `cartesia`
`agent.speak.provider.model_id`	String	The model ID to use
`agent.speak.provider.voice`	Object	Cartesia Voice configuration
`agent.speak.provider.voice.mode`	String	The voice mode to use
`agent.speak.provider.voice.id`	String	The voice ID to use
`agent.speak.provider.language`	String	Language setting
`agent.speak.endpoint`	Object	Must include url and headers
`agent.speak.endpoint.url`	String	Your Cartesia API endpoint URL
`agent.speak.endpoint.headers`	Object	Headers for authentication

Example

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "cartesia",
6         "model_id": "sonic-2",
7         "voice": {
8           "mode": "id",
9           "id": "a167e0f3-df7e-4d52-a9c3-f949145efdab"
10         },
11         "language": "en"
12       },
13       "endpoint": {
14         "url": "https://api.cartesia.ai/tts/bytes",
15         "headers": {
16           "x-api-key": "{{CARTESIA_API_KEY}}"
17         }
18       }
19     }
20   }
21 }

Amazon (AWS) Polly

For Amazon (AWS) Polly you can refer to this article for a list of available voices.

If no engine is specified, Amazon (AWS) Polly defaults to Standard. If the chosen voice doesn’t support Standard, you’ll get an error like: “Standard engine not supported for {voice}.” In that case, you must explicitly specify the correct engine.

Parameter	Type	Description
`agent.speak.provider.type`	String	Must be `aws_polly`
`agent.speak.provider.language_code`	String	The language code to use
`agent.speak.provider.voice`	String	The voice to use
`agent.speak.provider.engine`	String	The engine to use
`agent.speak.provider.credentials`	Object	The credentials to use

STS Example

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "aws_polly",
6         "language_code": "en-US",
7         "voice": "Matthew",
8         "engine": "standard",
9         "credentials": {
10           "type": "sts",
11           "region": "us-west-2",
12           "access_key_id": "{{AWS_ACCESS_KEY_ID}}",
13           "secret_access_key": "{{AWS_SECRET_ACCESS_KEY}}",
14           "session_token": "{{AWS_SESSION_TOKEN}}"
15         }
16       },
17       "endpoint": {
18         "url": "https://polly.us-west-2.amazonaws.com/v1/speech"
19       }
20     }
21   }
22 }

IAM Example

JSON

1 {
2   "agent": {
3     "speak": {
4       "provider": {
5         "type": "aws_polly",
6         "voice": "Joanna",
7         "language_code": "en-US",
8         "engine": "standard",
9         "credentials": {
10           "type": "iam",
11           "region": "us-east-2",
12           "access_key_id": "{{AWS_ACCESS_KEY_ID}}",
13           "secret_access_key": "{{AWS_SECRET_ACCESS_KEY}}"
14         }
15       },
16       "endpoint": {
17         "url": "https://polly.us-east-2.amazonaws.com/v1/speech"
18       }
19     }
20   }
21 }

Using multiple TTS providers

The speak object accepts both a single provider and an array of providers. When you supply an array, the Voice Agent uses the providers as an ordered fallback chain: it sends each TTS request to the first provider in the list and automatically falls back to the next provider if the request fails.

How fallback works

The agent sends the request to the first provider in the array.
If that provider returns an error or times out, the agent sends a SPEAK_REQUEST_FAILED warning over the WebSocket and retries with the next provider.
This continues through every provider in the array.
If all providers fail, the agent sends a FAILED_TO_SPEAK error and the turn produces no audio response.

The fallback is per-request — each new agent utterance starts again from the first provider. Provider order matters, so place your preferred provider first and your most reliable fallback last.

Fallback providers do not need to use the same provider.type. You can mix providers (for example, deepgram primary with an open_ai fallback) to maximize availability across independent infrastructure.

Example

JSON

1 {
2   "agent": {
3     "speak": [
4       {
5         "provider": {
6           "type": "deepgram",
7           "model": "aura-2-zeus-en"
8         }
9       },
10       {
11         "provider": {
12           "type": "open_ai",
13           "model": "tts-1",
14           "voice": "shimmer"
15         },
16         "endpoint": {
17           "url": "https://api.openai.com/v1/audio/speech",
18           "headers": {
19             "authorization": "Bearer {{OPENAI_API_KEY}}"
20           }
21         }
22       }
23     ]
24   }
25 }

What’s Next

Configure the Voice Agent

1	{
2	"speak": {
3	"provider": {
4	"type": "deepgram",
5	"model": "aura-2-thalia-en",
6	"speed": 0.9
7	}
8	}
9	}

1	{
2	"agent": {
3	"speak": {
4	"provider": {
5	"type": "cartesia",
6	"model_id": "sonic-2",
7	"voice": {
8	"mode": "id",
9	"id": "a167e0f3-df7e-4d52-a9c3-f949145efdab"
10	},
11	"speed": "normal"
12	}
13	}
14	}
15	}

1	{
2	"agent": {
3	"speak": [
4	{
5	"provider": {
6	"type": "deepgram",
7	"model": "aura-2-zeus-en"
8	}
9	},
10	{
11	"provider": {
12	"type": "open_ai",
13	"model": "tts-1",
14	"voice": "shimmer"
15	},
16	"endpoint": {
17	"url": "https://api.openai.com/v1/audio/speech",
18	"headers": {
19	"authorization": "Bearer {{OPENAI_API_KEY}}"
20	}
21	}
22	}
23	]
24	}
25	}