API Reference

Community

Blog

Starter Kit

Get Started

Payload definition for the message `named_entity_recognition`.

Named Entity Recognition

The most reliable state-of-the-art Speech to Text API provider

Welcome to Gladia

Gladia over vanilla Whisper?

Setup your Gladia account and start using the most reliable state-of-the-art Speech To Text API

Getting started

Get started with Gladia Pre-recorded STT API

Core features of the Gladia Pre-recorded STT API

Features

Detect speakers and understand who said what.

Speaker Diarization

Migration guide from Gladia V1 API to the V2 API

Migrate from V1 API

Get started with Gladia Real-time Speech to Text (STT) API

Core features of Gladia's real-time speech-to-text (STT) API 

Migrate to the latest version of Gladia's API

Migration guide from V1 to V2

Translate your transcriptions & subtitles

Translation

Get important information from your audio files

Summarization

The Named Entity Recognition model automatically identifies and categorizes key information in the audio.

Extract sentiments and emotions from the transcript.

Sentiment and Emotion Analysis

Detect potentially inappropriate content in your audio

Content Moderation

The Chapterization model segments the audio into distinct chapters, each with a descriptive headline and summaries

Chapterization

Ask any question or analysis, as you would do with an assistant

Audio to LLM

Gladia supports a variety of languages. Below, you'll find the list of all our supported languages.

Supported Languages

Rate limiting and transcriptions concurrency

Concurrency and Rate limits

Supported files & duration

Some code samples on how to integrate Gladia to third party services

Integration

Using Gladia for virtual meeting recordings.

Using Gladia for virtual meeting recordings

Introduction

Use your API key to authenticate your calls

Authentication

Understand the workflow to transcribe an audio file and get your result

Pre-recorded workflow

Understand the workflow for a live transcription session

Live workflow

Upload a file for use in a pre-recorded job.

Upload a file

Initiate a pre-recorded transcription job. Use the returned `id` and the [GET /v2/pre-recorded/:id](/api-reference/v2/pre-recorded/get) endpoint to obtain the results.

Initiate a transcription

Get pre-recorded transcription's status, parameters and result.

Get result

List all the pre-recorded transcriptions matching the parameters.

List transcriptions

Download the audio file used on a pre-recorded transcription.

Download audio file

Delete a pre-recorded transcription and all its data (audio file, transcription).

Delete transcription

Payload definition for the webhook event `transcription.created`.

Created

Payload definition for the webhook event `transcription.success`.

Success

Payload definition for the webhook event `transcription.error`.

Error

Payload definition for the callback event `transcription.success`.

Payload definition for the callback event `transcription.error`.

Initiate a live transcription job. Use the returned ws `url` to connect to the websocket and start sending audio chunks. Use the returned `id` and the [GET /v2/live/:id](/api-reference/v2/live/get) endpoint to obtain the status and results.

Initiate a session

Get live transcription's status, parameters and result.

List all the live transcriptions matching the parameters.

Download the audio file recorded during a live transcription.

Delete a live transcription and all its data (audio file, transcription).

Payload definition for sending an audio chunk in JSON format. You can also send it as binary directly.

Audio chunk

Payload definition to inform that the recording is over. After reception, no more audio chunk will be accepted and post-processing will start.

Stop recording

Payload definition for the message `transcript`.

Transcript

Payload definition for the message `sentiment_analysis`.

Sentiment Analysis

Payload definition for the message `post_transcript`.

Post Transcript

Payload definition for the message `post_final_transcript`.

Final transcript

Payload definition for the message `post_chapterization`.

Payload definition for the message `post_summarization`.

Payload definition for the [`audio_chunk`](/api-reference/v2/live/action/audio-chunk) acknowledgment.

Audio chunk acknowledge (ack)

Payload definition for the [`stop_recording`](/api-reference/v2/live/action/stop-recording) acknowledgment.

Stop recording acknowledge (ack)

Payload definition for the message `start_session`.

Start session

Payload definition for the message `start_recording`.

Start recording

Payload definition for the message `end_recording`.

End recording

Payload definition for the message `end_session`.

End session

Payload definition for the callback event `live.transcript`.

Payload definition for the callback event `live.named_entity_recognition`.

Payload definition for the callback event `live.sentiment_analysis`.

Payload definition for the callback event `live.post_transcript`.

Payload definition for the callback event `live.post_final_transcript`.

Payload definition for the callback event `live.post_chapterization`.

Payload definition for the callback event `live.post_summarization`.

Payload definition for the callback event `live.start_session`.

Payload definition for the callback event `live.start_recording`.

Payload definition for the callback event `live.end_recording`.

Payload definition for the callback event `live.end_session`.

Payload definition for the webhook event `live.start_session`.

Payload definition for the webhook event `live.start_recording`.

Payload definition for the webhook event `live.end_recording`.

Payload definition for the webhook event `live.end_session`.

(Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/init). Initiate a pre-recorded transcription job. Use the returned id and the [GET /v2/transcription/:id](/api-reference/v2/transcription/get) endpoint to obtain the results.

(Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/get). Get transcription's status, parameters and result.

(Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/list). List all the transcriptions matching the parameters.

(Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/get-audio). Download the audio file used on a transcription.

(Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/delete). Delete a transcription and all its data (audio file, transcription).

API Documentation

Upload

Pre-recorded endpoints

Pre-recorded webhooks

Pre-recorded callbacks

Live endpoints

Live WS actions

Live WS messages

Live callbacks

Live webhooks

Transcription (deprecated)

Named Entity Recognition