Gan Os Documentation

Home

API Reference

Visit our platform

This API can be used to list the inferences generated from a particular avatar.

List Avatar Videos

Avatar Id

Avatar Title

Created At

Unique identifier for the generated video from avatar(inference).

Inference Id

Input Text

Represents the CloudFront URL of the thumbnail, initially `null` while being generated, and returns the URL once available 

Thumbnail

Title

Cloudfront url of the generated inference video.

Video

AvatarInferenceDetails

AvatarInferenceStatus

APIKeyHeader

AvatarInferenceDetailsBulk

UnauthorizedException

EntityNotFoundException

ValidationException

ProcessException

Introduction

Speech

Avatar

Avatar Video Generation

Avatar Verification Errors

Sound Effects

Pricing Plans

Webhook

Retrieves a list of voices to generate the speech output from.

Get Voices

The Text-to-Speech (TTS) API converts text into natural-sounding speech and supports a wide range of Indian languages. This makes it ideal for various use cases, including creating voiceovers for multimedia, enhancing accessibility in applications, providing spoken directions in navigation systems, and facilitating interactive customer service.          

Text To Speech

Retrieves the history of the generated text to speech.

Text to Speech History

Create Avatar

List avatars

Use this API to fetch the avatar details.

Avatar Details

This API can be used to generate videos from the created avatars. To generate an inference video, you can provide either text or audio as input, by default priority would be given to the given audio.

Create Avatar Video

Use this API to fetch the details of a particular video.

Avatar Video Details

This endpoint can be used to bulk delete the avatars along with the associated inference videos.

Bulk Delete Avatars

This endpoint can be used to bulk delete the avatar inference videos by providing a list of avatar inference ids.

Delete avatar videos bulk

Use this API to get a passcode to use in the consent video.

Get Consent Passcode

This API can be used to submit a consent video, ensure that the video includes the passcode being spoken clearly. 
 
 The response indicates that the consent video has been submitted, but it does not confirm that the video has been successfully validated.

Submit Consent

Generates sound effects based on prompt and generation parameters.

Generate Sound Effect

Retrieves the history of generated sound effects inferences.

History

Retrieve the audio data for a given sound effects inference from S3 and return it in Base64-encoded format

Voices

TTS

Avatars

Consent

Sound Effects

List Avatar Videos

Authorizations

Query Parameters

Response