Speech-to-Text API
for call centers,
10x cheaper

Krisp Speech-to-Text API is designed to meet the needs of
innovative Call Center BPOs, at a fraction of the cost.

Green check markUp to 10x cheaper than the industry Green check markSupports all CX and Voice platforms out of the box Green check markData doesn’t leave the customer’s premise
AI Noise Cancellation

High-quality but 10x cheaper

Speech-to-Text
(starting price, per hour)
Streaming Speech-to-Text
(starting price, per hour)
PII Redaction
(starting price, per hour)
Krisp $0.04 $0.10 (coming soon) $0.02
AssemblyAI $0.12 $0.47 $0.08
Azure $0.18 $1.00 N/A
Deepgram $0.25 $0.35 $0.10
Google $0.96 $0.96 N/A
AWS $1.44 $1.44 $0.14

Krisp’s low price is possible because its proprietary algorithms
run Speech-to-Text and PII Redaction on the end user’s device
rather than in the cloud.

Who is it built for?

Krisp Speech-to-Text is perfect for Call Centers and BPOs wanting to build Speech Analytics, Customer QA or Agent Assist technologies to make their operations more effective. Speech-to-Text is a key building block for such technologies.
It’s also perfect for Enterprises that don’t want to share their internal or customer communication data with 3rd parties.

Krisp AI Assistant Action Items

Why is Krisp a perfect solution for you?

  • Krisp offers up to 10x lower pricing
  • Customer data is not shared with 3rd party providers, enabling maximum security
  • Out of the box, Krisp supports all CX and Voice platforms, making it super easy to set it up

Krisp AI Meeting Assistant summary

How Does it Work?

1
Install Krisp app on agents’ devices (the same app that provides Noise Cancellation and Accent Localization)
2
Turn on Speech-to-Text from Krisp’s web admin dashboard
3
Specify the private cloud where you want call transcripts to be uploaded (e.g. S3)

Once set up, every time a call ends, Krisp will upload the call transcript to the private cloud location, with < 1 second latency.

If enabled, Krisp will also record the calls and upload recordings to the same private cloud, along with call transcripts.

Krisp Call Center Transcription

High-quality Speech-to-Text
in 4 languages

Krisp Call Center Transcription

Krisp’s generated call transcripts go through several post-processing steps to make sure the transcript has the highest quality level:

Accuracy with a WER (Word Error Rate) of only 7.96%
Adds punctuation, capitalization, and numerical values
Assigns text to speakers with timestamps
If turned on, removes PII/PCI and filler words
Krisp support English, Spanish, French and German languages.
WER results (average 7.96%) on different datasets:
AMI17.39%
TED-LIUM3.75%
Earnings-2213.94%
Voxpopuli7.73%
LibriSpeech-clean1.92%
LibriSpeech-other4.26%
Common Voice 99.30%
GigaSpeech10.72%
SPGISpeech2.60%

See Call Center Transcription in action

See Krisp in Action video

Learn more about how your call center can benefit from Speech-to-Text API

form success icon Something Went Wrong!
form success icon Thanks for submitting the form! Our team will be in touch in 2-3 business days.
By contacting our team, you agree to the Terms of Use and Privacy Policy.
This form is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Enterprise-grade security

Hundreds of Call Centers and BPOs rely on Krisp today.

settings
Governance
  • Quick, easy deployment to all computers at once
  • User access and management
  • Centralized billing
  • Email, OAuth, and SSO user verification
settings
Privacy & Security
  • No voice data visible to Krisp servers
  • GDPR compliant
  • SOC-2 certified
  • Encryption in-transit and at-rest

Contact us to learn more!