Speech-to-Text Batch

Verbio leverages over 20 years of experience in voice AI and speech technologies to deliver cutting-edge products that perfectly match the needs of our trusted clients. Our STT batch product is ideal for use cases needing transcription of recorded audios, in 10 languages and over 20 dialects.

  • Human-to-Human Transcription for Speech Analytics
  • Podcast transcription
  • Medict

Here’s why:

Unparalleled accuracy

Our engines are based on state-of-the-art DNNs that have been trained with hundreds of thousands of audio, providing an extremely high Out-of-the-box accuracy, stable across domains.

Punctuation and advanced formatting

Adds capitalization and punctuation to the transcript and formats numbers, e-mails and much more. Ideal for analytics and use cases where a readable transcript is needed.

Standard APIs

Our interface offers seamless access through simple requests. Connect quickly via our REST API.

Speaker separation

STT batch can separate speakers either using diarization for mono files, and transcription of separate channels for stereo and multichannel audio with our multichannel feature.

Keyword boosting

By simply including keywords or a domain in the speech recognition request, you can configure the service to recognize specific utterances, like for example products, brands or specific domain terms.

Secure communications

We only use industry-standard encrypted channels for communication that guarantee a secure access to our platform. We are compliant with privacy policies and are SOCII certified.



Please check the following documentation for more information:

Speech-To-Text Batch documentation

Speech-To-Text Batch Plus documentation

Batch API

Quickstart guide for batch using Postman