Akool
Updated
Use an Akool avatar to represent your agent on video in a Conversational AI Platform agent.
Preview documentation
Akool provides AI-powered avatars with realistic facial expressions and lip-sync capabilities, enabling natural video conversations with your AI agents. Their platform offers a variety of pre-built avatars and supports custom avatar creation.
Sample configuration
The following example shows how to configure Akool as the agent's avatar when you create or update an agent. For a complete example, see Create an agent and start a session.
Akool supports BYOK only. It isn't available in managed mode. Store your Akool 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, AkoolAvatar, 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(...) # configure a TTS vendor with a 16,000 Hz sample rate
.with_avatar(
AkoolAvatar(
api_key=secret_ref("support_prod", "akool"),
avatar_id="<akool_avatar_id>",
additional_params={
"agora_uid": "<avatar_rtc_uid>",
"agora_token": "<avatar_rtc_token>",
},
)
)
)import { Agent, AkoolAvatar, 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(/* configure a TTS vendor with a 16,000 Hz sample rate */)
.withAvatar(
new AkoolAvatar({
apiKey: secretRef('support_prod', 'akool'),
avatarId: '<akool_avatar_id>',
additionalParams: {
agora_uid: '<avatar_rtc_uid>',
agora_token: '<avatar_rtc_token>',
},
}),
);// client is your configured Agora client
agent := agentkit.NewAgent(client).
WithStt( /* configure your ASR vendor */ ).
WithLlm( /* configure your LLM vendor */ ).
WithTts( /* configure a TTS vendor with a 16,000 Hz sample rate */ ).
WithAvatar(vendors.NewAkoolAvatar(vendors.AkoolAvatarOptions{
APIKey: agentkit.SecretRef("support_prod", "akool"),
AvatarID: "<akool_avatar_id>",
AdditionalParams: map[string]interface{}{
"agora_uid": "<avatar_rtc_uid>",
"agora_token": "<avatar_rtc_token>",
},
}))Add an avatar block to the pipeline. Set credential.mode to byok and credential.fields.api_key to the reference. In the following example, the key is stored as akool in the support_prod set:
"avatar": {
"enabled": true,
"credential": {
"mode": "byok",
"fields": {
"api_key": "$secrets.support_prod.akool"
}
},
"vendor": "akool",
"params": {
"agora_uid": "<avatar_rtc_uid>",
"agora_token": "<avatar_rtc_token>",
"avatar_id": "<akool_avatar_id>"
}
}Info
Akool avatars only support audio with a sample rate of 16,000 Hz. Using a TTS model configured with a different sample rate results in an error. Make sure that your TTS configuration matches this requirement.
Key parameters
The avatar block takes the following fields. In the SDKs, AkoolAvatar sets them from its options, and passes any other parameters from its additional parameters option to params.
enabledbooleanSet to true to show the avatar.
vendorstringSet to akool.
credentialobjectSet mode to byok and fields.api_key to a $secrets.<set>.<key> reference to your Akool API key.
Info
To purchase an Akool API key, contact Agora sales.
paramsobjectagora_uidstringThe unique identifier for the avatar's RTC connection. This must be different from other participants in the channel.
agora_tokenstringThe RTC token that authorizes the avatar to join the video channel. Generate this token using your Agora project credentials.
avatar_idstringThe unique identifier for the specific Akool avatar you want to use. Find available avatar IDs in your Akool dashboard.
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.