#Slow realtime transcription speeds with nova and nova2

1 messages · Page 1 of 1 (latest)

azure frost
#

I'm experiencing 3-4s of latency with both the nova and nova2 models. for testing purposes I'm reading from an audio file and streaming it to deepgram using the code below. What am I doing wrong?

@unkempt crest

const deepgramLive =  deepgramClient.transcription.live({
  punctuate: true,
  interim_results: false,
  language: "en-US",
  // model: "nova-2-ea",
  model: "phonecall",
  tier: "nova",
  encoding: "mulaw",
  sample_rate: 8000,
  keywords: keywords
});
crude juniperBOT
#

Thanks for asking your question. Please be sure to reply with as much detail as possible so we can assist you efficiently. Such as:

  • Provide the request_id if you've a question about a transcription response.
  • The options you used or the api.deepgram.com URL you sent your request to, including parameters.
  • Any code snippets you can include.
  • Any audio you can include, or if you can't share it here please email it to us at [email protected] and provide a link to this thread.
azure frost
#

here's a recent request ID 49b21d08-0677-4245-9ef1-cae2e956a640

unkempt crest
#

okay, so the real-time transcription will wait for a natural pause in the speech to finalise the utterance.

#

i would turn on interim results... you'll get a response several times a second. that utterance is complete when one includes is_final: true in the response