HeyGen Voice

HeyGen Voice Turbo

Fast speech generation from up to 5,000 characters of text. Choose from 24 library voices or clone a single speaker from a reference recording; only the first three minutes are used. Supports 39 languages with automatic detection and adjustable expressiveness. Returns 44.1 kHz WAV audio.

MAI-Voice-2

Microsoft high-fidelity expressive text-to-speech with multilingual MAI-Voice-2 prebuilt voices.

MAI-Voice-2.1

Microsoft expressive, high-fidelity text-to-speech for long-form narration, with 97 prebuilt voices across 23 languages.

MAI-Voice-2.1-Flash

Microsoft fast text-to-speech for assistants and interactive applications, with 97 prebuilt voices across 23 languages.

ACE-Step 1.5

ACE-Step 1.5 composes complete songs from text descriptions. Guide genre, mood, and structure with style tags and required custom lyrics. Generates up to 4 minutes of multi-track audio with vocals.

ACE-Step v1.5 Base

ACE-Step v1.5 Base is a Runware-hosted music model built for creator workflows, with stronger fidelity, more reliable stylistic consistency, and prompt-driven genre control for full-song generation.