Skip to main content
All MyVocal products share one public host, https://api.myvocal.ai, and one accessKey request header. Pick the product you need; each card starts at that product’s shortest working path. You do not need to create a voice or try every product first.

​
Choose a product

Text to Speech

Input: text and a voiceId (prebuilt or your own).
Result: an audio stream (normally audio/mpeg) in the response.
Start: TTS quickstart →

Speech to Text

Input: an uploaded recording, a public media URL, or live audio.
Result: a transcript to poll and download (Batch), or partial and final events over a WebSocket (Real-time).
Start: Batch quickstart → (live audio: Real-time quickstart, below)

Voice cloning

Input: your own mp3/wav/m4a recordings.
Result: a custom voiceId for Text to Speech or for AI Cover.
Start: How to use voices →

AI Cover

Input: a song file (mp3/wav) and a Cover voice.
Result: a cover version, reported to your callback URL and listed in Cover History.
Start: AI Cover quickstart →

Text to Music

Input: a creative brief (description, genre, moods, duration).
Result: an original song you poll for, then play or download as MP3.
Start: Text-to-Music quickstart →

Interpretation

Translate recorded audio or video with the file API, or stream live audio with the realtime API.File translation quickstartRealtime translation quickstart
Speech to Text has two starting points: the Batch quickstart for recordings and the Real-time quickstart for live audio.

​
Make your first request

First API request

Get your key, verify it with one free read call, then pick a product.

Authentication

The accessKey header, where to find your key and how to keep it safe.

API directory

Every endpoint, grouped by product.

​
Real-time Speech to Text SDKs

Server-side SDKs for the real-time Speech to Text API. They are optional: you can also call the REST and WebSocket API directly.

Install

Packages and runtimes.

Python

Python 3.10+

Java

Java 8+

Go

Go 1.22+

​
Voices and TTS models

  • Text to Speech and AI Cover take a voiceId. Cloning your own voice is optional; see How to use voices.
  • Text to Speech uses the default model path when you omit modelId, or the model you name with a public modelId such as myvocal_v3. See TTS Models & Migration for the list.

​
How results come back

Products return results in different ways. Use the mechanism of the product you integrate: For how Speech to Text, Text to Music and Interpretation charge Characters, see Characters and billing. Your plan and balance are returned by Get account information.