How to Choose the Right Speech-to-Text 3.7 Model (Full Transcript)

A quick guide to selecting Speech-to-Text 3.7, Realtime, or Realtime Agent for recordings, live conversations, and voice agents.
Download Transcript (DOCX)
Transcription editor
You wouldnt wear a scuba suit to a sprint pick the right speech-to-text model
Added on 11/18/2026
Speakers
add Add new speaker

[00:00:00] Speaker 1: You wouldn't wear a scuba diving suit for a sprinting race, or a football jersey for your wedding dance, or a three-piece suit to play tennis. And it's the same way with Speech AI. With the release of our Speech-to-Text 3.7 models, each model serves its own purpose and it's crucial that you use the right model for the right job. Speech-to-Text 3.7 is our asynchronous model for pre-recorded audio. It catches every detail in your audio recording, and with top speaker diarization performance, it's as close to perfect as it gets. 3.7 Realtime is built for live conversations, think meetings, calls, and captions. It comes with live speaker labels and a competitive word error rate without sacrificing latency. But what it doesn't do is turn-taking. If anything on your end needs to tell the model when a turn is over, then what you're looking for is 3.7 Realtime Agent. 3.7 Realtime Agent is built for voice agent use cases that require ultra-low latency while not sacrificing accuracy on numbers, short replies, even in scenarios with background noise or accented speech. And so it's the perfect foundation for your cascaded voice agent architecture. So those are our three new models released today. Remember to pick the right one for your use case, and let us know if you have any questions. Bye.

ai AI Insights
Arow Summary
The speaker introduces three Speech-to-Text 3.7 models and explains that each is designed for a different use case. Speech-to-Text 3.7 is an asynchronous model for pre-recorded audio, emphasizing detailed transcription and strong speaker diarization. Speech-to-Text 3.7 Realtime supports live conversations such as meetings, calls, and captions, offering live speaker labels, competitive accuracy, and low latency, but it does not handle turn-taking. Speech-to-Text 3.7 Realtime Agent is intended for voice agents that need turn-taking awareness, ultra-low latency, and reliable recognition of numbers and short responses in noisy or accented-speech conditions. The speaker urges users to select the model that fits their application.
Arow Title
Choosing the Right Speech-to-Text 3.7 Model
Arow Keywords
Speech-to-Text 3.7 Remove
asynchronous transcription Remove
pre-recorded audio Remove
speaker diarization Remove
realtime speech-to-text Remove
live speaker labels Remove
voice agents Remove
turn-taking Remove
low latency Remove
cascaded voice agents Remove
Arow Key Takeaways
  • Use Speech-to-Text 3.7 for detailed transcription of pre-recorded audio with strong speaker diarization.
  • Use Speech-to-Text 3.7 Realtime for live meetings, calls, and captions requiring low latency and live speaker labels.
  • Realtime does not provide turn-taking support for systems that need to know when a speaker has finished.
  • Use Speech-to-Text 3.7 Realtime Agent for voice agents requiring turn-taking, ultra-low latency, and strong performance on short replies, numbers, noise, and accents.
  • Model selection should be driven by the specific speech application and interaction requirements.
Arow Sentiments
Positive: The tone is upbeat, confident, and informative, presenting the new models as purpose-built solutions and encouraging users to choose the best fit.
Arow Enter your query
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript