$5 free credits when you sign up New FLUX.2 Klein model is now available NEW LTX-2 Now available via API NEW New TTS models — Qwen3 TTS and Chatterbox. NEW Music generation - Ace-Step 1.5 Turbo
Models Pricing Enterprise Docs
Text to Image Text to Speech Image to Text Image to Image Video to Text Image to Video
Sign in Get Started

deAPI platform changelog

Stay up to date with what shipped across landing pages, docs, playground and the API surface. Newest changes appear first.

Changes in:
API
Models
Pricing
Use-cases
Community

6 March 2026

deAPI Update: Voice Cloning, Music Generation, and New Contact Page

This update introduces voice cloning via API, music generation features, and a new contact page for Enterprise customers.

New Features

  • Voice cloning and voice design now available via API and in Playground.
  • Music Generation functionality added.
  • Music Generation use-case page created.
  • New contact page for Enterprise customers launched.

Improvements

  • Updated /pricing and /models endpoints to include Music Generation and Image upscaling.
Changes in:
API
Models
Docs

3 March 2026

deAPI Update: New Music Generation and Voice Cloning Features

This update introduces a new music generation module and voice cloning support.

New Features

  • New music generation module (Ace-Step 1.5 Turbo model) available via API.
  • Added Voice Cloning and Voice Design support for Qwen3 TTS via API.

Documentation

  • Documentation updated with new changes.

API Changes

Changes in:
Use-cases
Docs
MCP

26 February 2026

deAPI Update: New Use-Case Pages and MCP Repository Launch

We've introduced new use-case pages and launched the public MCP repository.

New Features

  • Added new use-case pages: OpenClaw Agent, Claude Code Skills.

Improvements

  • Updated existing use-case pages and regulations to align with the new landing page design.

Documentation

  • Public deAPI MCP repository is now available at GitHub.
Changes in:
API
Models

24 February 2026

deAPI Update: New Text-to-Speech Models Now Available

Introducing new text-to-speech models with enhanced features and capabilities.

New Features

  • Qwen3 TTS 12Hz 1.7B CustomVoice: Offers 9 premium voices (male & female) across 10 languages including EN, ZH, JA, KO, DE, FR, RU, PT, ES, IT. Features instruction-driven emotion and prosody control with streaming at 97ms latency.
  • Chatterbox: Supports 23 languages (EN, ES, FR, DE, ZH, JA, KO, AR, HI, PL, and more) with emotion exaggeration control and built-in AI watermarking.