The world's best models. One studio.

More video models

• Seedance 2.0ByteDanceNew

  ByteDance's reliable all-rounder: lifelike motion with sound, from text or a first frame with no real person in it.

  Try
• Seedance 2.0 FastByteDanceNew

  Seedance 2.0, faster and for less, up to 720p: quick takes with sound, from text or a first frame with no real person in it.

  Try
• Seedance 2.0 MiniByteDanceNew

  The lowest-priced Seedance 2.0: clips with sound up to 720p, for drafts and volume, from text or a first frame with no real person in it.

  Try
• Kling 3.0 Motion ControlKuaishouNew

  Moves the character in your image the way the person in a reference video moves, and keeps the face through turns, hands and hats. Billed by the length of the reference video.

  Try
• Grok Imagine Video 1.5xAINew

  xAI's newer video model: expressive motion with sound, up to 1080p, from text or a first frame.

  Try
• Grok Imagine Video 1.5 LitexAINew

  The light Grok Imagine 1.5: quick, very cheap clips with sound, from text or a first frame.

  Try

More image models

• Nano Banana 2.1GoogleNew

  Gemini Nano Banana 2.1: Google's newest image model, from 1K to 4K, with edits of up to 14 references.

  Try
• Nano Banana 2 LiteGoogleNew

  The light Nano Banana 2: quick 1K images and edits of up to 6 references, at about half the price.

  Try
• GPT Image 2.5 SunburstOpenAINew

  OpenAI's newest image model, built for precise edits: quality up to max, 4K, and up to 8 references.

  Try
• GPT Image 2.5 FlareOpenAINew

  The quicker GPT Image 2.5: quality up to max, 4K, and up to 8 references.

  Try
• FLUX 3 ImageBlack Forest LabsNew

  Black Forest Labs' FLUX 3: generation and edits with up to 10 references, up to 4K.

  Try
• Qwen-Image 3AlibabaNew

  Alibaba's newest image model, from 2026-07-21: images and edits of your own, with strong text in Chinese and English.

  Try

More voice and sound models

• Gemini 3.8 Flash-Lite TTSGoogleNew

  Gemini's lighter speech model: 30 voices, directed in plain words.

  Try
• S2.1 ProFish AudioNew

  Fish Audio's most natural speech. Direct a line with tags in the text, such as [whispering].

  Try
• S2 ProFish AudioNew

  Fish Audio's model before S2.1, at the same price and in the same voices.

  Try
• MiniMax Music 3MiniMaxNew

  Songs up to five minutes long from a style prompt and your lyrics. Without lyrics it makes an instrumental. A song can end before the length you ask for, which is what the run is billed.

  Try

• RodinDeemos

  Production-ready 3D assets from an image or a prompt.

  Try
• Rodin 2.5 FastDeemos

  Rodin 2.5 in seconds, at ten cents a model.

  Try
• Meshy 6Meshy

  Detailed, textured 3D models from an image.

  Try
• Meshy 6 Text to 3DMeshy

  Detailed, textured 3D models from a prompt.

  Try
• TRELLISMicrosoft

  Open-weight image to 3D, at two cents a model.

  Try
• Hunyuan3D 2Tencent

  A textured 3D model from one image, as a GLB. Without texture, a plain white mesh costs a third as much.

  Try

• Scribe v2ElevenLabs

  ElevenLabs' most accurate transcription: word timings, speaker labels and 90+ languages, from a sound or a video. Billed per started minute of the recording.

  Try
• Whisper Large v3OpenAI

  OpenAI's Whisper on fal's fast runtime: the cheapest way to transcribe hours of audio, in 99 languages, and it translates any of them into English. Segment timings, no speaker labels.

  Try