Cartesia
Updated
Use Cartesia for text-to-speech (TTS) in a Conversational AI Platform agent.
Preview documentation
Cartesia provides ultra-fast, low-latency text-to-speech with real-time streaming capabilities, optimized for interactive conversational AI applications.
Sample configuration
The following example shows how to configure Cartesia as the agent's TTS when you create or update an agent. For a complete example, see Create an agent and start a session.
Cartesia supports BYOK only. It isn't available in managed mode. Store your Cartesia API key in a secret set, and refer to it from the agent. For details, see Use your own provider keys.
from agora_agent import Agent, CartesiaTTS, secret_ref
# client is your configured Agora client
agent = (
Agent(client=client)
.with_stt(...) # configure your ASR vendor
.with_llm(...) # configure your LLM vendor
.with_tts(
CartesiaTTS(
api_key=secret_ref("support_prod", "cartesia"),
base_url="wss://api.cartesia.ai",
model_id="sonic-2",
voice_id="<voice_id>",
sample_rate=16000,
language="en",
)
)
)import { Agent, CartesiaTTS, secretRef } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(/* configure your ASR vendor */)
.withLlm(/* configure your LLM vendor */)
.withTts(
new CartesiaTTS({
apiKey: secretRef('support_prod', 'cartesia'),
baseUrl: 'wss://api.cartesia.ai',
modelId: 'sonic-2',
voiceId: '<voice_id>',
sampleRate: 16000,
language: 'en',
}),
);// client is your configured Agora client
sampleRate := vendors.SampleRate16kHz
agent := agentkit.NewAgent(client).
WithStt( /* configure your ASR vendor */ ).
WithLlm( /* configure your LLM vendor */ ).
WithTts(vendors.NewCartesiaTTS(vendors.CartesiaTTSOptions{
APIKey: agentkit.SecretRef("support_prod", "cartesia"),
BaseURL: "wss://api.cartesia.ai",
ModelID: "sonic-2",
VoiceID: "<voice_id>",
SampleRate: &sampleRate,
Language: "en",
}))Set credential.mode to byok and credential.fields.api_key to a reference to your Cartesia API key. In the following example, the key is stored as cartesia in the support_prod set:
"tts": {
"credential": {
"mode": "byok",
"fields": {
"api_key": "$secrets.support_prod.cartesia"
}
},
"vendor": "cartesia",
"url": "wss://api.cartesia.ai",
"params": {
"model_id": "sonic-2",
"voice": {
"mode": "id",
"id": "<voice_id>"
},
"output_format": {
"container": "raw",
"sample_rate": 16000
},
"language": "en"
}
}Key parameters
The tts block takes the following fields. In the SDKs, CartesiaTTS sets them from its options.
vendorstringSet to cartesia.
credentialobjectSet mode to byok and fields.api_key to a $secrets.<set>.<key> reference to your Cartesia API key. Get your API key from the Cartesia Console.
urlstringThe WebSocket URL for the Cartesia streaming API. For example, wss://api.cartesia.ai.
paramsobjectmodel_idstringThe identifier of the TTS model to use. For example, sonic-2.
voiceobjectVoice configuration object.
modestringVoice selection mode. Use id to select by voice identifier.
idstringThe identifier of the selected voice for speech synthesis.
output_formatobjectAudio output format configuration
containerstringAudio container format for the output stream.
sample_ratenumber- Default value
- 16000
- Possible values
80001600022050240004410048000
Audio sampling rate in Hz
languagestringTarget language for speech synthesis.
Caution
The parameters listed on this page are validated for use with the Conversational AI Platform. Required parameters must be provided as documented. Any additional parameters in params are passed through directly to Cartesia without validation. For a full list of supported options, refer to the Cartesia TTS documentation.
This integration is fully supported for use with the Conversational AI Platform. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.