ARES
Updated
Use ARES for speech recognition (ASR) in a Conversational AI Platform agent.
Preview documentation
Adaptive Recognition Engine for Speech (ARES) provides built-in real-time speech-to-text, offering seamless integration with low latency and reliable performance for conversational AI applications.
Sample configuration
The following example shows how to configure ARES as the agent's ASR when you create or update an agent. For a complete example, see Create an agent and start a session.
ARES is available in managed mode only. Agora provides ARES, and you don't need a provider account or API key. For details, see Use managed mode.
from agora_agent import Agent, AresSTT
# client is your configured Agora client
agent = (
Agent(client=client)
.with_stt(AresSTT(keywords=["Agora", "Conversational AI", "RTC"]))
.with_llm(...) # configure your LLM vendor
.with_tts(...) # configure your TTS vendor
)import { Agent, AresSTT } from 'agora-agents';
// client is your configured Agora client
const agent = new Agent({ client })
.withStt(new AresSTT({ keywords: ['Agora', 'Conversational AI', 'RTC'] }))
.withLlm(/* configure your LLM vendor */)
.withTts(/* configure your TTS vendor */);// client is your configured Agora client
agent := agentkit.NewAgent(client).
WithStt(vendors.NewAresSTT(vendors.AresSTTOptions{
Keywords: []string{"Agora", "Conversational AI", "RTC"},
})).
WithLlm( /* configure your LLM vendor */ ).
WithTts( /* configure your TTS vendor */ )Set credential.mode to managed in the asr block:
"asr": {
"credential": { "mode": "managed" },
"vendor": "ares",
"language": "en-US",
"params": {
"keywords": ["Agora", "Conversational AI", "RTC"]
}
}Key parameters
The asr block takes the following fields. In the SDKs, AresSTT sets them from its options, and passes any other ARES parameters from its additional parameters option to params.
| Parameter | Description |
|---|---|
vendorstring | Set to |
credentialobject | How the agent authenticates with ARES. Set |
languagestring | One or more BCP-47 language tags identifying the languages used for agent interaction. To recognize multiple languages, pass the tags as a single comma-separated string, for example, Semantic end-of-speech detection ( |
paramsobject |
|
