Sarvam

Updated

Use Sarvam for speech recognition (ASR) in a Conversational AI Platform agent.

Preview documentation

You're reading the Conversational AI Platform (Preview) docs. Switch to Main.

Sarvam ASR provides real-time speech-to-text with low latency and reliable performance for Indian languages.

Sample configuration

The following example shows how to configure Sarvam as the agent's ASR when you create or update an agent. For a complete example, see Create an agent and start a session.

Sarvam supports BYOK only. It isn't available in managed mode. Store your Sarvam 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, SarvamSTT, secret_ref

# client is your configured Agora client
agent = (
    Agent(client=client)
    .with_stt(
        SarvamSTT(
            api_key=secret_ref("support_prod", "sarvam"),
            language="hi-IN",
        )
    )
    .with_llm(...)  # configure your LLM vendor
    .with_tts(...)  # configure your TTS vendor
)
import { Agent, SarvamSTT, secretRef } from 'agora-agents';

// client is your configured Agora client
const agent = new Agent({ client })
  .withStt(
    new SarvamSTT({
      apiKey: secretRef('support_prod', 'sarvam'),
      language: 'hi-IN',
    }),
  )
  .withLlm(/* configure your LLM vendor */)
  .withTts(/* configure your TTS vendor */);
// client is your configured Agora client
agent := agentkit.NewAgent(client).
	WithStt(vendors.NewSarvamSTT(vendors.SarvamSTTOptions{
		APIKey:   agentkit.SecretRef("support_prod", "sarvam"),
		Language: "hi-IN",
	})).
	WithLlm( /* configure your LLM vendor */ ).
	WithTts( /* configure your TTS vendor */ )

Set credential.mode to byok and credential.fields.api_key to a reference to your Sarvam API key in a secret set. In the following example, the key is stored as sarvam in the support_prod set:

"asr": {
  "credential": {
    "mode": "byok",
    "fields": {
      "api_key": "$secrets.support_prod.sarvam"
    }
  },
  "vendor": "sarvam",
  "language": "hi-IN",
  "params": {
    "language": "hi-IN"
  }
}

Key parameters

The asr block takes the following fields. In the SDKs, SarvamSTT sets them from its options, and passes any other Sarvam parameters from its additional parameters option to params.

asrrequired
vendorstring
required

Set to sarvam.

credentialobject
required

How the agent authenticates with Sarvam. Set mode to byok and fields.api_key to a $secrets.<set>.<key> reference to your Sarvam API key. Get your API key from the Sarvam dashboard.

languagestring
required

The language code for transcription, for example, hi-IN. Set to unknown for automatic language detection.

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 Sarvam without validation. For a full list of supported options, refer to the Sarvam 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.