{"models":[{"endpoint_id":"pixverse/music-video/vibemv","metadata":{"display_name":"PixVerse VibeMV","category":"audio-to-video","description":"PixVerse VibeMV generates music videos from audio, with optional character references and lyric subtitles. It supports visual style presets, custom style references, five aspect ratios, and output at 720p or 1080p.","status":"active","tags":["audio-to-video","music-video","pixverse","vibemv"],"updated_at":"2026-09-21T19:54:52.100Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaac960/8mih2vKZ0s5GqPG_pA0cH.jpg","model_url":"https://fal.run/pixverse/music-video/vibemv","license_type":"commercial","date":"2026-09-17T12:35:02.123Z","group":{"key":"pixverse-music-video","label":"VibeMV"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"elevenlabs/music/v2.5","metadata":{"display_name":"Elevenlabs Music v2.5","category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music v2.5!","status":"active","tags":["music","text-to-music"],"updated_at":"2026-10-02T19:10:00.967Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa6adb/-Z3Ays503mRIC-atq70g8.jpg","model_url":"https://fal.run/elevenlabs/music/v2.5","license_type":"commercial","date":"2026-09-14T17:20:06.936Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"elevenlabs/music/v2","metadata":{"display_name":"Elevenlabs Music v2","category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music v2!","status":"active","tags":["music","text-to-music"],"updated_at":"2026-10-02T19:10:00.967Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa6ac9/dGujDO5lw_IneNzkkfJBe.jpg","model_url":"https://fal.run/elevenlabs/music/v2","license_type":"commercial","date":"2026-09-14T17:17:25.899Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/music-3","metadata":{"display_name":"MiniMax Music 3","category":"text-to-audio","description":"MiniMax Music 3 is a high-performance music generation model for creating complete songs up to five minutes long","status":"active","tags":["sfx","audio","effects",""],"updated_at":"2026-08-18T17:00:49.092Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa6363a/E6MV5Yy0mhJ2pOzNHcHAU.jpg","model_url":"https://fal.run/minimax/music-3","license_type":"commercial","date":"2026-08-13T19:47:14.143Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"sonilo/v1.1/video-to-video-music","metadata":{"display_name":"V1.1 Video to Video Music","category":"video-to-video","description":"Generates perfectly synced music for any video. Return a licensed music soundtrack ready for commercial use (optional preservation of the original speech in video)","status":"active","tags":["music","editing","restoration"],"updated_at":"2026-07-28T15:49:32.356Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa31db6/9QPgZEb8A9cdW-BdmK1Ri.jpg","model_url":"https://fal.run/sonilo/v1.1/video-to-video-music","license_type":"commercial","date":"2026-07-21T08:10:22.171Z","group":{"key":"sonilo-v11","label":"Video to Video (music)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-outpainting","metadata":{"display_name":"Stable Audio 3 Small Music Base Audio Outpainting","category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio outpainting is the foundational 459 million parameter checkpoint that extends music tracks via causal continuation guided by text prompts.","status":"active","tags":["music","extension","continuation"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b9b0c/2gdxA9DEL1uyWlprJCdq8_fc0f082c9b354f6e9befbc9813d6b891.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/base/audio-outpainting","license_type":"commercial","date":"2026-05-25T09:16:57.882Z","group":{"key":"SA3","label":"Audio Outpainting Small Music Base"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-inpainting","metadata":{"display_name":"Stable Audio 3 Small Music Base Audio Inpainting","category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio inpainting is the foundational 459 million parameter checkpoint for editing or filling selected music segments guided by text prompts.","status":"active","tags":["music","editing","restoration"],"updated_at":"2026-07-01T04:59:17.080Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b9b0d/4uEUhNCfIlvttfEsO9w8U_f367e57452f44cbda40ffcaf2bb6a9f4.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/base/audio-inpainting","license_type":"commercial","date":"2026-05-25T09:09:43.951Z","group":{"key":"SA3","label":"Audio Inpainting Small Music Base"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/base/audio-to-audio","metadata":{"display_name":"Stable Audio 3 Small Music Base Audio to Audio","category":"audio-to-audio","description":"Stable Audio 3 Small Music Base audio-to-audio is the foundational 459 million parameter checkpoint that transforms input music into new variations up to 2 minutes guided by text prompts.","status":"active","tags":["music","style-transfer","remix"],"updated_at":"2026-07-01T04:59:17.080Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b9b10/scDouGSsSQQF7yHNTa5hX_156730bac7c1485896425347d095b77b.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/base/audio-to-audio","license_type":"commercial","date":"2026-05-25T09:02:23.290Z","group":{"key":"SA3","label":"Audio to Audio Small Music Base"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/base/text-to-audio","metadata":{"display_name":"Stable Audio 3","category":"text-to-audio","description":"Stable Audio 3 Small Music Base is the foundational 459 million parameter checkpoint generating full music compositions up to 2 minutes from text prompts, intended as the unmodified base for fine-tuning.","status":"active","tags":["music","on-device","lightweight"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b202c/-1VabDgY8w--qmHnWfvTi_f76bd896adb540eb9c26b21ed83cc2c7.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/base/text-to-audio","license_type":"commercial","date":"2026-05-22T15:43:34.371Z","group":{"key":"SA3","label":"Text to Audio Small Music Base"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/audio-outpainting","metadata":{"display_name":"Stable Audio 3 Small Music Audio Outpainting","category":"audio-to-audio","description":"Stable Audio 3 Small Music audio outpainting is a 459 million parameter latent diffusion model that extends music compositions beyond their original endpoint via causal continuation.","status":"active","tags":["music","extension","continuation"],"updated_at":"2026-07-01T04:59:17.080Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b9b0d/Kh-tnlUj_gy0u61oHqq56_fd08d0fe65544232975c56508110aa0e.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/audio-outpainting","license_type":"commercial","date":"2026-05-25T09:14:11.330Z","group":{"key":"SA3","label":"Audio Outpainting Small Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/audio-inpainting","metadata":{"display_name":"Stable Audio 3 Small Music Audio Inpainting","category":"audio-to-audio","description":"Stable Audio 3 Small Music audio inpainting is a 459 million parameter latent diffusion model that fills in or reworks selected segments of a music track guided by text prompts.","status":"active","tags":["music","editing","restoration"],"updated_at":"2026-07-01T04:59:17.080Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b9b0f/N2740TzF9Szx8jXGxpLmP_65f836db1db94202948361b0c99232e4.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/audio-inpainting","license_type":"commercial","date":"2026-05-25T09:05:54.494Z","group":{"key":"SA3","label":"Audio Inpainting Small Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/audio-to-audio","metadata":{"display_name":"Stable Audio 3","category":"audio-to-audio","description":"Stable Audio 3 Small Music audio-to-audio is a 459 million parameter latent diffusion model that transforms input music into new variations up to 2 minutes guided by text prompts.","status":"active","tags":["music","style-transfer","remix"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9afef4/YhJSYE2movbXiqKa-cIfh_bb2831ac8a374cceac99fdfea79ebdbc.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/audio-to-audio","license_type":"commercial","date":"2026-05-22T15:47:07.213Z","group":{"key":"SA3","label":"Audio to Audio Small Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/small/music/text-to-audio","metadata":{"display_name":"Stable Audio 3 Small Music Text to Audio","category":"text-to-audio","description":"Stable Audio 3 Small Music is a 459 million parameter latent diffusion model that generates full stereo music compositions up to 2 minutes from text prompts, lightweight enough for on-device deployment.","status":"active","tags":["music","on-device","lightweight"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9afee6/G8pcVD9MpzzHo2binrk2Q_24695711c8d54f76bef2b83ad27e8b7b.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/small/music/text-to-audio","license_type":"commercial","date":"2026-05-22T15:41:12.143Z","group":{"key":"SA3","label":"Text to Audio Small Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"sonilo/v1.1/text-to-music","metadata":{"display_name":"Sonilo V1.1 Text to Music","category":"text-to-audio","description":"Generates licensed, commercial-use-safe music from a single text prompt, with full control over style, mood, instrumentation, and exact duration.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-13T17:21:15.566Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9cce58/2fkn-QJvDeqArMhlb66vr_9e400a7a1fd841f38bed933eeb6aa3fe.jpg","model_url":"https://fal.run/sonilo/v1.1/text-to-music","license_type":"commercial","date":"2026-06-03T11:27:07.889Z","group":{"key":"sonilo-v11","label":"Text to Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"sonilo/v1.1/video-to-music","metadata":{"display_name":"V1.1","category":"video-to-audio","description":"Analyzes your video’s pacing, mood, and timing to generate a frame-synced, licensed, commercial-use-safe soundtrack in seconds.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-13T17:21:15.566Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2fa5/jHE-xiu94lGuFQ6TRzyJ0_42eae911d4d0441e91d0e870274c4898.jpg","model_url":"https://fal.run/sonilo/v1.1/video-to-music","license_type":"commercial","date":"2026-06-03T11:34:42.346Z","group":{"key":"sonilo-v11","label":"Video to Music"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax-music/v2.5","metadata":{"display_name":"Minimax Music 2.5","category":"text-to-audio","description":"MiniMax Music 2.5 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-04-21T02:06:24.967Z","is_favorited":null,"thumbnail_url":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a959abf%2F6tnoknThTQqVLnqwuX7Xv_97eaac1b47904e9cb8f02fedba07132e.jpg/tr:w-1920,q-80/6tnoknThTQqVLnqwuX7Xv_97eaac1b47904e9cb8f02fedba07132e.webp","model_url":"https://fal.run/fal-ai/minimax-music/v2.5","license_type":"commercial","date":"2026-04-11T06:22:56.672Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax-music/v2.6","metadata":{"display_name":"Minimax Music 2.6","category":"text-to-audio","description":"MiniMax Music 2.6 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-04-21T02:05:12.810Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a959abf/bBuGvGbMCy6eYzC8n05Ql_7f5c08f2be3f495cb9847f89217309a8.jpg","model_url":"https://fal.run/fal-ai/minimax-music/v2.6","license_type":"commercial","date":"2026-04-11T06:21:38.930Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/music","metadata":{"display_name":"Elevenlabs Music","category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music!","status":"active","tags":["music","text-to-music"],"updated_at":"2026-09-15T03:31:04.015Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a875694/SZffdb8layV90JxfN5fkP_d2048a658d9e4dc9973598f3542833a0.jpg","model_url":"https://fal.run/fal-ai/elevenlabs/music","license_type":"commercial","date":"2025-12-22T15:22:56.999Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax-music/v2","metadata":{"display_name":"Minimax Music","category":"text-to-audio","description":"Generate music from text prompts using the MiniMax Music 2.0 model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","status":"active","tags":["music","audio"],"updated_at":"2026-04-21T17:51:57.425Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/jnrLOiQsmRXqYCI_haHe5_63de465a7ccb447bb3bf9ed6c0c1c88e.jpg","model_url":"https://fal.run/fal-ai/minimax-music/v2","license_type":"commercial","date":"2025-10-30T22:33:42.886Z","group":{"key":"minimax-music","label":"v2.0"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax-music/v1.5","metadata":{"display_name":"MiniMax (Hailuo AI) Music v1.5","category":"text-to-audio","description":"Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","status":"active","tags":["music"],"updated_at":"2026-06-24T11:34:22.087Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92cc/aUmpKwGz4nPeB6JqmAyxr_pKYFLz4u.png","model_url":"https://fal.run/fal-ai/minimax-music/v1.5","license_type":"commercial","date":"2025-09-11T22:14:58.124Z","group":{"key":"minimax-music","label":"v1.5"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"cassetteai/music-generator","metadata":{"display_name":"music generator","category":"text-to-audio","description":"CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.\n\n","status":"active","tags":["music","cassetteai"],"updated_at":"2026-07-09T17:51:06.273Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa1964b/JxxMXPoYkeJlLq6AJ89vN.jpg","model_url":"https://fal.run/CassetteAI/music-generator","license_type":"commercial","date":"2025-03-27T15:08:50.013Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax-music","metadata":{"display_name":"MiniMax (Hailuo AI) Music","category":"text-to-audio","description":"Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.","status":"active","tags":["music"],"updated_at":"2026-06-24T11:27:47.551Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f9226/ErX7ZBppvx3nKC_mTIZOs_5HfTRVWx.png","model_url":"https://fal.run/fal-ai/minimax-music","license_type":"commercial","date":"2024-12-17T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/lyria-3.5","metadata":{"display_name":"Lyria 3.5","category":"text-to-audio","description":"Lyria 3.5 is Google DeepMind's latest music generation model, and you can generate almost any type of music with it","status":"active","tags":["music","text-to-music","speech"],"updated_at":"2026-09-30T01:19:34.727Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa8afe/VbJWL93MNQf7eBuxjBEJO.jpg","model_url":"https://fal.run/google/lyria-3.5","license_type":"commercial","date":"2026-09-19T19:11:59.582Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3-trainer","metadata":{"display_name":"Stable Audio 3 Trainer","category":"training","description":"Stable Audio 3 LoRA Trainer fine-tunes Stable Audio 3 base models on paired audio-caption datasets, producing compact LoRA weights that adapt generation toward a custom music style, sound palette, or domain.","status":"active","tags":["music","audio","sfx","lora"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9dde78/H-0IiF_EcppSobAaoIZKt_f8595f702fbd4a228de9f4e00f209934.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3-trainer","license_type":"commercial","date":"2026-06-11T13:05:07.132Z","highlighted":false,"kind":"training","pinned":false,"inference_endpoint_ids":["fal-ai/stable-audio-3/medium/text-to-audio/lora","fal-ai/stable-audio-3/medium/base/text-to-audio/lora"]}},{"endpoint_id":"fal-ai/stable-audio-3/medium/base/text-to-audio","metadata":{"display_name":"Stable Audio 3 Medium Base Text to Audio","category":"text-to-audio","description":"Stable Audio 3 Medium Base is the foundational 1.4 billion parameter text-to-audio checkpoint generating stereo music up to 6 minutes, intended as the unmodified base for custom fine-tuning workflows.","status":"active","tags":["music","audio","stereo"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9afef7/T9QQlYMsBV4QUMzKXNl1T_fc97eeec050f46548ae2276c4599aaea.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/medium/base/text-to-audio","license_type":"commercial","date":"2026-05-22T15:14:47.254Z","group":{"key":"SA3","label":"Text to Audio Medium Base"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-3/medium/text-to-audio","metadata":{"display_name":"Stable Audio 3","category":"text-to-audio","description":"Stable Audio 3 Medium is a 1.4 billion parameter latent diffusion model that generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for safe commercial use.","status":"active","tags":["music","audio","stereo"],"updated_at":"2026-07-01T04:56:00.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9b2029/-fLLWd3eyZFK2trS5WZSm_3fcc28379b8e43cba15bd36bf4e573d3.jpg","model_url":"https://fal.run/fal-ai/stable-audio-3/medium/text-to-audio","license_type":"commercial","date":"2026-05-22T15:10:08.656Z","group":{"key":"SA3","label":"Text to Audio Medium"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/lyria3/pro","metadata":{"display_name":"Lyria 3 Pro","category":"text-to-audio","description":"Lyria 3 Pro is the latest music model from Google","status":"active","tags":["audio","sfx"],"updated_at":"2026-07-01T04:49:53.442Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9af59e/gZo8cVQPq90KMeAU-tQ7H_5144bb99c04b47038d174c4068bfcada.jpg","model_url":"https://fal.run/fal-ai/lyria3/pro","license_type":"commercial","date":"2026-05-20T11:18:49.537Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/lyria3","metadata":{"display_name":"Lyria3","category":"text-to-audio","description":"Lyria 3 is most recent music model from Google","status":"active","tags":["audio","music","sfx"],"updated_at":"2026-08-26T20:55:32.910Z","is_favorited":null,"thumbnail_url":"https://refinery.fal.media/url/https%3A%2F%2Fv3b.fal.media%2Ffiles%2Fb%2F0a94048f%2FbSx2MSBmQSPqHu3eKueYS_25a4c220ab8c4f67851f04f8e62b8445.jpg/tr:w-1920,q-80/bSx2MSBmQSPqHu3eKueYS_25a4c220ab8c4f67851f04f8e62b8445.webp","model_url":"https://fal.run/fal-ai/lyria3","license_type":"commercial","date":"2026-03-30T07:27:13.890Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/lyria2","metadata":{"display_name":"Lyria2","category":"text-to-audio","description":"Lyria 2 is Google's latest music generation model, you can generate any type of music with this model.","status":"active","tags":["music","stylized"],"updated_at":"2026-07-01T04:13:51.657Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Sound-4.jpg","model_url":"https://fal.run/fal-ai/lyria2","license_type":"commercial","date":"2025-05-20T20:05:49.336Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/yue","metadata":{"display_name":"YuE: Lyrics to Song","category":"text-to-audio","description":"YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs.","status":"deprecated","tags":["music"],"updated_at":"2026-05-26T23:04:46.866Z","is_favorited":null,"thumbnail_url":"https://fal.media/files/lion/JAvN_VTh4kcTwtLBuS-A-_152d79bde246442ea7d8a0e2422d90d1.jpg","model_url":"https://fal.run/fal-ai/yue","license_type":"commercial","date":"2025-01-28T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"lightricks/ltx-2.5/audio-to-video/pro","metadata":{"display_name":"Ltx 2.5 Audio to Video Pro","category":"audio-to-video","description":"LTX-2.5 is Lightricks' open-source audio-video model. This endpoint generates video timed to a supplied audio clip in a quality-optimized mode, for final visuals synchronized to music, dialogue, or a soundtrack.","status":"active","tags":["stylized","transform","lip-sync"],"updated_at":"2026-08-14T23:11:35.262Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5ebb1/x2M962iL_WzU9M8R6D5fd.jpg","model_url":"https://fal.run/lightricks/ltx-2.5/audio-to-video/pro","license_type":"commercial","date":"2026-08-11T14:40:23.860Z","group":{"key":"ltx-2.5-api","label":"Audio to Video (Pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"lightricks/ltx-2.5/audio-to-video/fast","metadata":{"display_name":"Ltx 2.5 Audio to Video Fast","category":"audio-to-video","description":"LTX-2.5 is Lightricks' open-source audio-video model. This endpoint generates video timed to a supplied audio clip in a speed-optimized mode — useful for music-driven content, dialogue-led shorts, and ads keyed to a track.","status":"active","tags":["stylized","transform","lip-sync"],"updated_at":"2026-08-14T23:11:35.262Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5ebdc/MKczu_IE0mraWaSReg-gx.jpg","model_url":"https://fal.run/lightricks/ltx-2.5/audio-to-video/fast","license_type":"commercial","date":"2026-08-11T14:39:15.854Z","group":{"key":"ltx-2.5-api","label":"Audio to Video (Fast)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-25/audio-to-audio","metadata":{"display_name":"Stable Audio 2.5","category":"audio-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","status":"active","tags":["audio"],"updated_at":"2026-06-24T11:47:07.472Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92e0/AZXaxD049-BtyQY433DPD_hA9hXLtT.png","model_url":"https://fal.run/fal-ai/stable-audio-25/audio-to-audio","license_type":"commercial","date":"2025-09-10T11:51:47.856Z","group":{"key":"stable-audio-25","label":"Audio to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-25/text-to-audio","metadata":{"display_name":"Stable Audio 2.5","category":"text-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","status":"active","tags":["audio"],"updated_at":"2026-06-24T10:39:31.754Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91ae/mtqDUea-jzlnWg_odMe1j_bB5cIBlf.png","model_url":"https://fal.run/fal-ai/stable-audio-25/text-to-audio","license_type":"commercial","date":"2025-09-10T11:50:27.666Z","group":{"key":"stable-audio-25","label":"Text to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-25/inpaint","metadata":{"display_name":"Stable Audio 25","category":"audio-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","status":"active","tags":["audio"],"updated_at":"2026-06-24T16:21:09.243Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f939c/Ylxvt7v73QKZ0FWrD-HVA_5qMPrdpT.png","model_url":"https://fal.run/fal-ai/stable-audio-25/inpaint","license_type":"commercial","date":"2025-09-10T11:46:09.286Z","group":{"key":"stable-audio-25","label":"Inpaint"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/pixverse/sound-effects","metadata":{"display_name":"PixVerse Sound Effects","category":"video-to-video","description":"Add immersive sound effects and background music to your videos using PixVerse sound effects  generation","status":"active","tags":["audio","utility"],"updated_at":"2026-06-17T18:20:01.178Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","model_url":"https://fal.run/fal-ai/pixverse/sound-effects","license_type":"commercial","date":"2025-07-07T20:56:55.765Z","group":{"key":"pixverse-45","label":"Sound Effects"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ace-step/audio-to-audio","metadata":{"display_name":"ACE Step Audio To Audio","category":"audio-to-audio","description":"Generate music from a lyrics and example audio using ACE-Step","status":"active","tags":["audio-to-audio","audio-edit"],"updated_at":"2026-06-24T11:38:01.535Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92cf/hzzRn42s_9muLz0OmggMY_AltNTjLY.png","model_url":"https://fal.run/fal-ai/ace-step/audio-to-audio","license_type":"commercial","date":"2025-05-11T17:53:31.579Z","group":{"key":"ace-step","label":"Audio to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ace-step/prompt-to-audio","metadata":{"display_name":"ACE Step Prompt To Audio","category":"text-to-audio","description":"Generate music from a simple prompt using ACE-Step","status":"active","tags":["text-to-audio","text-to-music"],"updated_at":"2026-06-24T11:04:55.945Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91b4/vrSrTlTF5lgNXOblHW2w7_rCiFN1PF.png","model_url":"https://fal.run/fal-ai/ace-step/prompt-to-audio","license_type":"commercial","date":"2025-05-11T17:51:47.356Z","group":{"key":"ace-step","label":"Prompt to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ace-step","metadata":{"display_name":"ACE Step","category":"text-to-audio","description":"Generate music with lyrics from text using ACE-Step","status":"active","tags":["text-to-audio","text-to-music"],"updated_at":"2026-06-24T10:42:28.949Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91b3/9VL1XeX8WQ9GzM0BA_gC7_MYE49kWH.png","model_url":"https://fal.run/fal-ai/ace-step","license_type":"commercial","date":"2025-05-08T21:47:06.754Z","group":{"key":"ace-step","label":"Lyrics to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/got-ocr/v2","metadata":{"display_name":"GOT OCR 2.0","category":"vision","description":"GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.","status":"active","tags":["optical character recognition","high-res","utility"],"updated_at":"2026-06-24T11:48:57.176Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92da/BEb6pE3CEr6Y89AkI_kEe_WN3XECwa.png","model_url":"https://fal.run/fal-ai/got-ocr/v2","license_type":"commercial","date":"2025-02-12T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/diffrhythm","metadata":{"display_name":"DiffRhythm: Lyrics to Song","category":"text-to-audio","description":"DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.","status":"active","tags":["music"],"updated_at":"2026-06-24T11:45:25.115Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92d5/RI4o31rYekV5K2GHIYOeI_4bbU0wiJ.png","model_url":"https://fal.run/fal-ai/diffrhythm","license_type":"commercial","date":"2025-03-04T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio","metadata":{"display_name":"Stable Audio Open","category":"text-to-audio","description":"Open source text-to-audio model.","status":"active","tags":["music"],"updated_at":"2026-06-24T10:35:22.168Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91ac/Y4wJF8Zssld_xUqoxrUFL_SRbvyWYq.png","model_url":"https://fal.run/fal-ai/stable-audio","github_url":"https://huggingface.co/stabilityai/stable-audio-open-1.0/blob/main/LICENSE","license_type":"commercial","date":"2024-01-04T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}}],"next_cursor":null,"has_more":false}