When you are sending text to our TTS websocket from an LLM, you will need to send a Flush message whenever the LLM finishes a response to indicate the end of the conversation. This allows Deepgram to generate the audio from its existing text buffer without waiting for additional text.

In other cases in real-time text-to-speech processing, there are scenarios where you may need to force the server to process all (or flush) unprocessed speech-to-text data immediately. Deepgram supports a Flush message to handle such situations.

What is the Flush Message?

Flush forces the generation of audio from our internal text buffer. When your LLM has finished outputting its last token, this is useful if you want our TTS to generate its next audio based on what's in the text buffer until that point.

🚧

Very frequent flushes can affect audio output quality.

Using the Flush Message

Required

To send the Flush message, you need to send the following JSON message to the server:

Sending Flush

{
    "type": "Flush"
}

Flush Confirmation

Upon receiving the Flush message, the server will process all remaining text data and return the final audio results.

Example Response

{
 
"type": "Flushed",
"sequence_id": 0
}

Conclusion

Using the Flush message with Deepgram's API allows for precise control over the finalization of speech-to-text processing. This feature is essential for scenarios requiring immediate processing of the remaining data, ensuring accurate and timely results.