# Model Series

Explore model series and compare their image, video, and audio models.

26 series

[View All Models](<https://www.modellix.ai/explore.md>)

![CosyVoice](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[CosyVoice](<https://www.modellix.ai/series/cosyvoice.md>)

CosyVoice is an open-source multilingual TTS model that generates natural, human-parity speech with zero-shot voice cloning in real time.

4 models

![Fun ASR](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[Fun ASR](<https://www.modellix.ai/series/fun-asr.md>)

FunASR is an open-source, industrial-grade speech recognition toolkit that turns audio into accurate text, with built-in VAD, punctuation, and speaker verification.

1 models

![Gemini ASR](<https://img.modellix.ai/modelix-models-image/20260916/gemini-color.png?v=1&w=640&h=640>)

[Gemini ASR](<https://www.modellix.ai/series/gemini-asr.md>)

Gemini Transcribe — Google's dedicated ASR model that turns speech into precise, speaker-labeled text in 85+ languages, in real time.

1 models

![Gemini Omni](<https://img.modellix.ai/modelix-models-image/20260916/gemini-color.png?v=1&w=640&h=640>)

[Gemini Omni](<https://www.modellix.ai/series/gemini-omni.md>)

Gemini Omni — Google's natively multimodal "any-in, any-out" model that turns text, images, audio, and video into editable, physics-aware video, with image and audio outputs on the way.

9 models

![Gemini TTS](<https://img.modellix.ai/modelix-models-image/20260916/gemini-color.png?v=1&w=640&h=640>)

[Gemini TTS](<https://www.modellix.ai/series/gemini-tts.md>)

Gemini TTS — Google's native speech model that turns text (and a style prompt) into expressive, multi-speaker audio, in Flash and Pro flavors.

3 models

![GPT Image](<https://img.modellix.ai/modelix-models-image/20260916/openai.png?v=1&w=640&h=640>)

[GPT Image](<https://www.modellix.ai/series/gpt-image.md>)

GPT Image — OpenAI's native image generation model that turns text prompts into precise, high-fidelity images with strong prompt-following and accurate text rendering.

6 models

![Grok Imagine](<https://img.modellix.ai/modelix-models-image/20260916/grok.png?v=1&w=640&h=640>)

[Grok Imagine](<https://www.modellix.ai/series/grok-imagine.md>)

Grok Imagine is xAI's cross-modal generative model that creates and edits images and videos from text, image, or video input, with native synchronized audio.

14 models

![Grok Voice](<https://img.modellix.ai/modelix-models-image/20260916/grok.png?v=1&w=640&h=640>)

[Grok Voice](<https://www.modellix.ai/series/grok-voice.md>)

Grok Voice is xAI's real-time conversational speech model that lets Grok listen and talk back naturally, with expressive, low-latency, multi-persona voice interaction.

2 models

![Hailuo](<https://img.modellix.ai/modelix-models-image/20260916/hailuo-color.png?v=1&w=640&h=640>)

[Hailuo](<https://www.modellix.ai/series/hailuo.md>)

Hailuo is MiniMax's AI video generation model that turns text or image prompts into smooth, cinematic, physically believable clips with strong motion and character consistency.

6 models

![HappyHorse](<https://img.modellix.ai/modelix-models-image/20260916/happyhorse.png?v=1&w=640&h=640>)

[HappyHorse](<https://www.modellix.ai/series/happyhorse.md>)

HappyHorse is Alibaba's open-source AI video generation model that produces short clips with synchronized audio in a single pass, topping text-to-video and image-to-video leaderboards.

7 models

![Kling](<https://img.modellix.ai/modelix-models-image/20260916/kling-color.png?v=1&w=640&h=640>)

[Kling](<https://www.modellix.ai/series/kling.md>)

Kling is Kuaishou's AI video generation model that turns text or image prompts into high-quality, realistic, cinematic videos with strong motion and character consistency.

23 models

![MAI ASR](<https://img.modellix.ai/modelix-models-image/20260916/microsoft-color.png?v=1&w=640&h=640>)

[MAI ASR](<https://www.modellix.ai/series/mai-asr.md>)

MAI-Transcribe is Microsoft's multilingual speech-to-text model that delivers fast, highly accurate transcription even in noisy, overlapping, or low-quality audio, and ranks first on the FLEURS benchmark.

1 models

![MAI Image](<https://img.modellix.ai/modelix-models-image/20260916/microsoft-color.png?v=1&w=640&h=640>)

[MAI Image](<https://www.modellix.ai/series/mai-image.md>)

MAI-Image is Microsoft's in-house text-to-image model that turns text prompts into high-quality, photorealistic images and currently ranks among the top image generation models.

4 models

![MiniMax](<https://img.modellix.ai/modelix-models-image/20260916/minimax-color.png?v=1&w=640&h=640>)

[MiniMax](<https://www.modellix.ai/series/minimax.md>)

MiniMax's video generation models are a family of multimodal video systems that turn text, images, and audio into high-quality, cinematic clips with native synchronized sound, strong motion, and up to 2K resolution.

8 models

![MiniMax Speech](<https://img.modellix.ai/modelix-models-image/20260916/minimax-color.png?v=1&w=640&h=640>)

[MiniMax Speech](<https://www.modellix.ai/series/minimax-speech.md>)

MiniMax Speech is MiniMax's text-to-speech model family that generates natural, expressive, multilingual speech with zero-shot voice cloning and controllable emotion and pace.

3 models

![Nano Banana](<https://img.modellix.ai/modelix-models-image/20260916/nanobanana-color.png?v=1&w=640&h=640>)

[Nano Banana](<https://www.modellix.ai/series/nano-banana.md>)

Nano Banana is Google's Gemini image generation and editing model that turns text prompts into images and performs precise, conversational edits while keeping characters and scenes consistent.

10 models

![PixVerse](<https://img.modellix.ai/modelix-models-image/20260916/pixverse-color.png?v=1&w=640&h=640>)

[PixVerse](<https://www.modellix.ai/series/pixverse.md>)

PixVerse is AIsphere's AI video generation model that turns text or image prompts into stylized, high-quality videos with strong motion and effects, from realistic clips to anime styles.

13 models

![Qwen Audio](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[Qwen Audio](<https://www.modellix.ai/series/qwen-audio.md>)

Qwen Audio is Alibaba's multimodal audio-language model that understands speech, sound, and music and can generate text or spoken audio responses across multiple languages.

2 models

![Qwen Image](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[Qwen Image](<https://www.modellix.ai/series/qwen-image.md>)

Qwen Image is Alibaba's text-to-image model that turns prompts into high-quality images with strong prompt following and accurate, well-rendered text, especially bilingual Chinese and English.

4 models

![Seedance](<https://img.modellix.ai/modelix-models-image/20260916/bytedance-color.png?v=1&w=640&h=640>)

[Seedance](<https://www.modellix.ai/series/seedance.md>)

Seedance is ByteDance's video generation model that turns text or image prompts into smooth, cinematic, multi-shot videos with strong motion, realism, and character consistency.

13 models

![Seedream](<https://img.modellix.ai/modelix-models-image/20260916/bytedance-color.png?v=1&w=640&h=640>)

[Seedream](<https://www.modellix.ai/series/seedream.md>)

Seedream is ByteDance's text-to-image model that turns prompts into high-quality, photorealistic images with strong prompt following, accurate text rendering, and solid bilingual Chinese and English support.

7 models

![Veo](<https://img.modellix.ai/modelix-models-image/20260916/google-color.png?v=1&w=640&h=640>)

[Veo](<https://www.modellix.ai/series/veo.md>)

Veo is Google DeepMind's video generation model that turns text or image prompts into high-quality, cinematic videos with native synchronized audio and strong physical realism.

6 models

![Vidu](<https://img.modellix.ai/modelix-models-image/20260916/vidu-color.png?v=1&w=640&h=640>)

[Vidu](<https://www.modellix.ai/series/vidu.md>)

Vidu is Shengshu Technology's video generation model that turns text or image prompts into high-quality, realistic videos with strong reference-to-video consistency and coherent motion.

24 models

![Wan](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[Wan](<https://www.modellix.ai/series/wan.md>)

Wan is Alibaba's open-source video generation model family that turns text or image prompts into high-quality, cinematic videos with strong motion, physics, and native audio.

11 models

![Whisper](<https://img.modellix.ai/modelix-models-image/20260916/openai.png?v=1&w=640&h=640>)

[Whisper](<https://www.modellix.ai/series/whisper.md>)

Whisper is OpenAI's open-source speech recognition model that transcribes and translates multilingual audio into accurate text with strong robustness to noise and accents.

1 models

![Z Image](<https://img.modellix.ai/modelix-models-image/20260916/qwen-color.png?v=1&w=640&h=640>)

[Z Image](<https://www.modellix.ai/series/z-image.md>)

Z-Image is Alibaba Tongyi's efficient open-source text-to-image model that turns prompts into high-quality photorealistic images with accurate bilingual Chinese and English text rendering at fast speed.

1 models
