
MiniMax Music 3.0 is MiniMax's 11.1B-parameter open-weights music model that turns a musical description and optional lyrics into a complete, fully arranged and mixed song of up to five minutes - vocals, instrumentation and production included - in a single generation, with section-tag control over the arrangement and vocal or instrumental output.

MiniMax Lyrics Generation is a dedicated lyric-writing model that turns a one-line theme into a complete, professionally structured set of song lyrics - title, style tags, and sections marked with [Verse]/[Chorus] structure tags - and can also edit, continue, or restructure existing lyrics, with output directly usable as the lyrics input of MiniMax's music models.

Doubao‑Audio‑Generate‑1.0 is Doubao Voice’s next‑generation audio‑generation engine. The industry‑first commercial tool creates film‑grade audio with just one prompt. It eliminates cumbersome audio‑engineering work. Creators generate publish‑ready radio dramas, podcasts and branded audio easily, shifting from a simple voice‑generator to an AI audio director. It serves audiobooks, serialized episodes and commercial audio for high‑quality narrative‑driven production.

MiniMax text-to-speech (Turbo): fast, low-latency speech from text with selectable preset voices, speed, volume and pitch.

MiniMax text-to-speech (HD): natural, high-fidelity speech from text with selectable preset voices, speed, volume and pitch.

xAI TTS v1 is a high-fidelity text-to-speech model that converts text into natural, expressive speech with sub-second latency, supporting 20 languages and 80+ voices with fine-grained delivery control.

MiniMax text-to-music (latest): generate a full vocal or instrumental song from a style prompt plus lyrics with [Verse]/[Chorus] structure tags. Synchronous single-call generation.

ElevenLabs' fastest and most emotive voice model: expressive speech in 90+ languages, with inline delivery tags such as [cheerfully] and [whispers], and multi-speaker dialogue in a single request.

ElevenLabs' low-latency voice model: the expressiveness, inline delivery tags and multi-speaker dialogue of ElevenLabs v4 at half the price.

ElevenLabs v3 Text-to-Speech model. High-quality speech generation from text prompts.

Clone a reusable voice from a 5-30 second speech sample (or from a previously generated video) and get a voice_id the Kling 4.0 reference-to-video and video-edit models accept, plus an audition clip.

Alibaba's flagship text-to-speech model for premium voice work: multilingual and dialect synthesis with free-style instruction control over emotion, tone, role, speed, and volume, plus high-robustness voice cloning from noisy reference audio.

Alibaba's low-latency text-to-speech model for real-time interaction: broad language and Chinese dialect coverage with free-style instruction control, tuned for voice assistants, live dialogue, and customer service.

Alibaba's low-latency 3.1-generation text-to-speech model: rich system voices covering multiple foreign languages and Chinese dialects (Shanghainese, Cantonese, Northeastern, Sichuanese, and more), with free-style instruction control over emotion, tone, role, speed, and volume. Tuned for first-packet latency in real-time interaction.

Alibaba's 3.0-generation flagship text-to-speech model for social and companion scenarios: natural, expressive flagship system voices with free-style instruction control over emotion, tone, role, speed, and volume.

MiniMax's latest high-fidelity text-to-speech model: natural, expressive speech in 40 languages with inline interjection tags such as (laughs) and (sighs), emotion control, and selectable voices.

MiniMax's latest fast, low-cost text-to-speech model: natural speech in 40 languages with inline interjection tags such as (laughs) and (sighs), emotion control, and selectable voices.

Suno V6 text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics, with variety and target duration controls. Async; returns 2 tracks per generation.

Suno V6 Wild via APIMart: the experimental V6 variant with bolder, less conventional arrangements. Same modes and pricing as chirp-v6. Async; returns 2 tracks per generation.

Suno V6 Mini via APIMart: the lighter, faster V6 variant for drafts and short clips. Same modes and pricing as chirp-v6. Async; returns 2 tracks per generation.

Gemini text-to-speech (3.1 Flash): latest-generation expressive speech from text with 30 prebuilt voices and natural-language style control. Powered by gemini-3.1-flash-tts-preview.

Gemini text-to-speech: expressive, controllable speech from text with 30+ prebuilt voices (Kore, Puck, Charon, Aoede...). Powered by gemini-2.5-flash-preview-tts.

Gemini text-to-speech (Pro): studio-quality, expressive speech from text with 30 prebuilt voices and natural-language style control. Powered by gemini-2.5-pro-preview-tts.