Blog

Starter Kit

API Reference

Playground

Support

Get Clone Voices List

Location

Message

Error Type

ValidationError

Description

Files

Model

Name

Speaker

VoiceCloneInfoSchemas

APIVoiceCloneInfoResponse

HTTPValidationError

This is the documentation for the Topmediai API. You can use this API to use our service programmatically, this is done by using your x-api-key. You can get your x-api-key by request our Get API Key Web page on [Get API Key](https://www.topmediai.com/api/text-to-speech-api/). Our API is experimental so all endpoints are subject to change.

Introduction

Gets a list of all available voices for us.

Get Voice List

Converts text into speech using a voice of your choice and returns audio.

Text To Speech

Clone Voice

Delete Clone Voice

Get the remaining rights and interests information of the current x-api-key.

Get Api Key Info

Gets a list of all available singers for us.

Get Singer List

Use your files or youtube links to do a cover and return the audio.

AI Cover

Get VC Voices List

Use your files to do a voice change and return the audio.

AI Voice Change

AI Lyrics

Use your lyrics or param to do a music and return the audio.

AI Music Generator

Music generation task submission endpoints: 
1. Make a request with the required parameters (parameters are described in detail in the schema below). 
2. the endpoint will return the song information, including the song id and audio audition and image routing and task processing status (stream, error, complete). 
3. Song id can query song information and generation status through the query interface. 
4. In particular, do not use the V2 interface for arguments or responses in V1, it is just not allowed

Submit the music generation task

Querying the music generation status.

After using the extension feature in /v2/submit, a new part2 song will be generated, and using the concat endpoint,you can link the part1 and part2 songs together, so that the task will have an integrated song.If you extend it several times, that is, if you have parts 1, 2, 3, and 4, using the concat endpoint will link parts 1, 2, 3, and 4 into a song;

Text-to-Speech

Clone-Voice

X-API-Key-Info

AI-Song-Cover

AI-Voice-Change

AI-Music-Generator

Get Clone Voices List

Headers

Query Parameters

Response