Pricing
Speech to Text
Our pricing is based on the audio duration, charged per second. This means you only pay for the exact length of the audio you transcribe. For example, if your audio is 61 seconds long, you will be charged for 61 seconds, not 2 minutes.
Model
Price per minute
Pulse
$0.00583
Pulse + Diarization
$0.01
Pulse + Streaming**
$0.0075
Cosmos*
$0.01
Cosmos + Diarization**
$0.015
Astro (Deprecated)
$0.02083
Astro + Diarization (Deprecated)
$0.025
*Cosmos is the most accurate model, and the speed is still acceptable. ✅ Recommended for most use cases.
** Streaming API will be charged based on the duration of the WebSocket connection, not the audio or speech time.
Last updated