Pricing
Choose the right pricing model for your needs and start using the most powerful, inclusive, and accurate speech-to-text engine available on the market.
Pricing Models
$0 (4 hours free per month – 2 hours of Enhanced, 2 hours of Standard)
All 48 languages available
All features included
No contract, no credit card required upfront
Choice of Standard and Enhanced*
Deploy in the Cloud
Pricing Models
$0 (4 hours free per month – 2 hours of Enhanced, 2 hours of Standard)
All 48 languages available
All features included
No contract, no credit card required upfront
Choice of Standard and Enhanced*
Deploy in the Cloud
$1.25 per hour for Standard or $1.90 per hour for Enhanced*
4 hours free per month (2 hours of Enhanced, 2 hours of Standard)
All 48 languages available
All features included
No contract
Online support available (Mon-Fri, 9-5pm GMT)
Deploy in the Cloud
Up to 2,000 hours usage limit per month (1,000 hours of Enhanced, 1,000 hours of Standard)
Speak to Sales to discuss bespoke contracts
All 48 languages available
All features included
Choice of Standard or Enhanced*
Online support available (Mon-Fri, 9-5pm GMT)
Deploy in the Cloud, On-Premises or Hybrid
200+ hours per month required
If you have any questions about the pricing plan and your specific needs, contact our Sales Team.
Speak to SalesNeed our help? Contact our Support Team.
Contact Us
*Choosing Standard or Enhanced
Our standard operating point is world-leading in terms of accuracy and speed, but we understand there are times when an even greater degree of accuracy is required. This is why we’ve introduced our new enhanced operating point. At the forefront of voice technology, we’ve successfully integrated self-supervised learning into our software to give you the results you need.
Explore Our Cutting-Edge Speech-to-Text
Try for FreeConfidence Scores
Visualize the confidence of every word in the transcript.
Entity Formatting
Improve the professionalism of your transcripts with numeral recognition.
Speaker Diarization
Detect and label different speakers within the same channel.
Channel Diarization
Detect and label different speakers on up to six streams or channels.
Low Latency Finals
Define the context of transcriptions and use it to automatically correct words.
Automatic Sample Rate Detection
Determine the sample rate of each media file and apply the most appropriate transcription model.
All Major File Formats Supported
Support all major audio and video formats so you can reduce the time it takes to prepare files.
Advanced Punctuation
Use an extensive set of supported punctuation marks to optimize the speed and ease of transcription.
Custom Dictionary and Sounds Feature
Add a set of context-specific words to the dictionary to enhance your transcription accuracy.
Profanity Tagging
Words are automatically tagged as profanity in the transcription JSON output for use in post-processing.
Speaker Change
Easily identify a change of speaker within your transcript and improve its readability.
Notifications
Use callback to receive a notification when your job is complete. The notification can also include your transcription output.
Disfluencies
Words are automatically tagged which are considered to be hesitation or indecision in transcription JSON output for use in post-processing.
Partials
Transcriptions are returned as soon as transcript data is available, without the need to wait for additional context.
Transcript Finalization
Provides highly accurate transcripts and can automatically correct words to match the given context.
Flexible Endpointing
Ensure output formatting is kept consistent by flexibly overriding when a transcription’s finals are returned.