By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.

Speech-to-Text API

Speech-to-Text (STT) APIs enable developers to embed automatic transcription into any voice-enabled app. APIs are built on top of highly accurate and trainable deep learning asr models and we support both batch and streaming use cases.

* No credit card required.
Trusted by Companies building amazing products
Transcribe audio at scale,
on our Cloud or yours

Invoke our STT APIs using our highly scalable cloud service or deploy a containerized version of Voicegain in your VPC or datacenter. Our APIs can convert audio/video files in batch or a real-time media stream into text and we support 40+ audio formats.

Accuracy

89%

On a broad benchmark, our accuracy of 89% is on par with the very best

Languages

8

Talk to us in English, Spanish, German, Portuguese, Korean (more coming)

VPC

5

Tested on compute instances on Google, AWS, Azure, IBM & Oracle

CCaaS/CPaaS

10+

Integrates with Twilio, Genesys, FreeSWITCH and other CCaaS and CPaaS platforms

Simple to use,
Flexible to meet your needs
  • Accurate and Affordable
    Our APIs are disruptively priced and accuracy is better or on par with the best
  • Multiple Language Support
    English, Spanish, Portuguese, German, Korean. Coming Soon-> Dutch, French and Hindi
  • Flexible Deployment
    Invoke as a cloud service or deploy in your VPC/datacenter
  • Fast Offline Processing
    Process audio 100x faster than real-time
  • Real-time Speech Adaptation
    Use Hints, class tokens and Grammars to get higher accuracy
  • Train Custom Models
    Train acoustic & language models to get unmatched accuracy
  • Streaming Support
    Stream using WebSockets or using telephony (SIPREC, MRCP, etc)
  • Speaker Diarization
    Diarize mono channel audio to separate speakers
  • CCaaS/CPaaS support
    Integrate with most popular CPaaS/CPaaS platforms
  • NVIDIA GPUs
    Runs on NVIDIA GPU compute instances from Google, AWS & Azure
FAQs
Can I access the API documentation?
How are Voicegain STT APIs priced?
Do you offer support?
How can I stream audio to Voicegain?
What languages do you currently
support?
Where is my data processed and
stored?
How do you safeguard my data?
Integrations
Audio Sources
Bot Frameworks
Meeting Platforms
Check out our blog for insights, benchmarks, sample code, and more
Voicegain Blog
What our customers are saying..
Sign up for an app today
* No credit card required.

Enterprise

Interested in customizing the ASR or deploying Voicegain on your infrastructure?

Contact Us →