Unified API for Speech To Text and NLP

Access all Speech-To-Text and NLP providers using this vendor-agnostic open API. Apply ASR, NLP and NLU tasks from a large catalog of providers.

Access all speech to text & NLP providers through a simple API.

Why Unified API?

A single API for speech-to-text conversion as well as NLP.

This API can be used to access many different speech-to-text and natural language processing products from a single interface.

Multi Provider flexibility.

Easily compare, switch between, and try out different speech-to-text (STT) and natural language processing (NLP) providers.

No vendor lock-in

Our provider agnostic format for transcript and transcript metadata storage allows you to build without worrying about provider specific workflows and implementation details.

Use the right AI engine for the job

Whether mitigating downtime, or benchmarking accuracy, with this API, leveraging the strengths of different providers is now easy. Try out new models and keep up to date on new features from different providers.

Effortless ML pipelines for anyone

Pipeline ASR and NLP tasks by simply stating the tasks you want, and the API will stitch them together while abstracting away provider specific job handling and callback mechanisms.

Standardized transcript formats

standardized format, with adapters built for each provider, keeps this API maintainable and extensible. Easily add new Providers and functionality that integrates nicely with the rest of the API and pipelines.

Access to NLP models

NLP tasks we support: Sentiment, Questions, Summary, Action Items, Filler Word Detection, Entity Detection and Follow Ups

Transcript Intelligence

Access to the NLP model’s intelligence

Get deeper meanings from transcripts to data-driven insights from conversations.


Extracting the main topics discussed in a transcription, processed by an nlp model from an audio or video file.


Transcript summarization can summarize text in a transcript into points to remember by neglecting non-informative text, and converting relevant information into large text that is easy to comprehend.

Entity Detection

Entity Detection, also known as Entity Extraction (NER), is a data extraction approach that identifies key entities such as company name, product name, numbers, events, and location etc, from the transcription.

Sentiment Analysis

Sentiment Analysis can help detect emotional value in conversations, by retrieving positive, negative, and neutral statements in the transcript, which can be considered as valuable feedback.

PII Redaction

PII Redaction can help hide or erase personally identifiable information (PII) content such as name, address, bank account details, ssn etc, from your transcript.


Sentences in a transcript can be detected as questions by use of a pre-trained NLP model. The Questions, along with the type of questions can be detected.

Action Item

Detect action items in the transcript of a recorded meet. The tasks that come up during the meetings are automatically noted, making it for easy follow up.

Follow ups

Detect follow-up activities in the transcript of a recorded meet, as you can schedule a follow-up meeting with ease with automatic follow-ups.

Transcription Features

All in one powerful speech recognition API

Use our simple speech-to-text API to get all of the advanced AI functionality in one API.

Batch Transcription

Batch transcription is a service where you may transcribe large audio files, send transcription into storage, retrieve and use stored files whenever required.

Real-Time Transcription

Enable live transcriptions by using our Bot transcription services, that will transcribe live meetings on integrated platforms such as Zoom and Google Meet etc.

Send Bot to Meeting

Send a bot into a live meeting and perform tasks such as live-transcriptions, generate meeting notes, highlight insights and also, record the meeting.

Custom Vocabulary

Improve your transcription quality by adding a Custom vocabulary list, that can vary from the usage of company specific names and terms, to colloquial words used by different people around the world.

Speaker diarization

Speaker Diarization feature can break-up an audio recording into segments of multiple detected speakers. Each segment consists of a speaker, that can be labelled throughout the transcript.

Multi Language Support

We provide Multiple Language transcription support.

Transcription to NLP

Analyze generated transcriptions by use of Natural Language Processing (NLP), and achieve continuously improved transcription quality and efficiency.

Open source

AI engine’s code is open-source, making it easy for developers to adopt and build on top of their existing system, without worrying about any vendor lock-ins.

Confidence Scores

The Confidence Score specifies the ML / NLP model's certainty of the accuracy of correct predictions made by an algorithm.


Try it here!

Make API Call

Select Language

Select Speech-To-Text Provider

Transcript NLP/NLU









API Call

This playground shows cached responses for public users. Please to run actual queries.
curl --request POST \
--url https://api.exemplary.ai/v1/transcript \
--header 'Accept: application/json' \
--header 'Authorization: Bearer __api_key__' \
--header 'Content-Type: application/json' \
--data '
"url": "https://bit.ly/..elon.mp4",
"provider": "deepgram",
"speaker_labels": true,
"language": "auto"