Chirp 3, the latest generation of Google's multilingual Automatic Speech Recognition (ASR)-specific generative models offered by Google Cloud's Speech-to-Text (STT) API v2, is available for [Voice transcription](https://docs.cloud.google.com/agent-assist/docs/transcription).

## Set up

Follow these steps to enable transcription with Speech-to-Text Chirp 3.

### Console


When you create or update a conversation profile using the [Agent Assist console](https://agentassist.cloud.google.com/), follow these steps to configure Speech-to-Text settings to use the Chirp 3 model.

1. Click **Conversation profiles**.
2. Click the name of your profile.
3. Navigate to the **Speech to Text Config** section.
4. Choose **Chirp 3** for the model.
5. (Optional) Select **Use Long Form Model for AA Telephony SipRec Integration** if the audio is transmitted through Telephony Integration.
6. (Optional) Configure **Language Code** and up to one **Alternative Language Codes** for [language-restricted transcription](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model#perform_a_language-restricted_transcription).
7. (Optional) Configure **auto** as the language code for [language-agnostic transcription](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model#perform_a_language-agnostic_transcription).
8. (Optional) Configure **Phrases for speech adaptation** to improve accuracy with [model adaptation](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model#improve_accuracy_with_model_adaptation).

### REST API


You can call the API directly to create or update a conversation profile. Enable STT V2 with the `ConversationProfile.sttConfig.useSttV2` field, as shown in the following example.
Example Configuration:

```json
{
"name": "projects/PROJECT_ID/locations/global/conversationProfiles/CONVERSATION_PROFILE_ID",f
"displayName": "CONVERSATION_PROFILE_NAME",
"automatedAgentConfig": {
},
"humanAgentAssistantConfig": {
  "notificationConfig": {
    "topic": "projects/PROJECT_ID/topics/FEATURE_SUGGESTION_TOPIC_ID",
    "messageFormat": "JSON"
  },
  "humanAgentSuggestionConfig": {
    "featureConfigs": [{
      "enableEventBasedSuggestion": true,
      "suggestionFeature": {
        "type": "ARTICLE_SUGGESTION"
      },
      "conversationModelConfig": {
      }
    }]
  },
  "messageAnalysisConfig": {
  }
},
"sttConfig": {
  "model": "chirp_3",
  "useSttV2": true,
},
"languageCode": "en-US"
}
```

<br />

## Best practices

Follow these suggestions to get the most from voice transcription with Chirp 3 model.

### Audio streaming

To maximize Chirp 3 performance, send audio in near real time. This means if you have X seconds of audio, stream it in roughly X seconds. Break your audio into small chunks, each with a frame size of 100 ms. For more audio streaming best practices, see the [Speech-to-Text documentation](https://docs.cloud.google.com/speech-to-text/v2/docs/best-practices).

### Use speech adaptation

Use transcription with Chirp 3 speech adaptation only with inline phrases configured in the conversation profile.

### Use without extended streaming

When you use Chirp 3 for voice transcription, avoid enabling [extended streaming](https://docs.cloud.google.com/agent-assist/docs/extended-streaming). Extended streaming requires a model that supports the [single utterance](https://docs.cloud.google.com/speech-to-text/docs/reference/rpc/google.cloud.speech.v1#google.cloud.speech.v1.StreamingRecognitionConfig.FIELDS.bool.google.cloud.speech.v1.StreamingRecognitionConfig.single_utterance) configuration.

## Regional and language support

Chirp 3 is available for all [Speech-to-Text languages](https://docs.cloud.google.com/speech-to-text/v2/docs/chirp_3-model#language_availability_for_transcription) with different launch readiness, and in all [Agent Assist regions](https://docs.cloud.google.com/agent-assist/docs/regionalization) except `northamerica-northeast1`, `northamerica-northeast2`, and `asia-south1`.

## Quotas

The number of transcription requests using the Chirp 3 model is limited by the `SttV2StreamingRequestsPerMinutePerResourceTypePerRegion` quota with `chirp_3` labeled as the resource type. See the Google Cloud [quotas guide](https://docs.cloud.google.com/docs/quotas/view-manage#managing_your_quota_console) for information on quota usage and how to request a quota increase.

For quotas, transcription requests to the global and US multi-region Dialogflow endpoints are in the `us-central1` region.