ACE-Step v1.5 Turbo

ACE-Step 1.5 XL Turbo

ACE-Step 1.5 XL Turbo uses a 4B music generation architecture with distilled 8-step inference. Create music from text, transform a reference track into a cover, replace a segment, or extend audio before or after the source. Supports optional lyrics, musical key, tempo, and vocal language.

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.

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

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

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.

ElevenLabs v4 Turbo

Lower-latency ElevenLabs v4 text-to-speech with inline audio tags and custom voice IDs.