Model catalog
Audio models
Browse every available audio model, organized by family and ready to open with the right creation workflow.
36 models13 families
ElevenLabs
ElevenLabs · 8 models
ElevenLabsNewElevenLabs Audio IsolationSeparate vocals from background noise and music in any audio file using ElevenLabs' audio isolation model.
ElevenLabsNewElevenLabs Music v1Generate original music tracks from text descriptions using ElevenLabs' music generation model. Supports both vocal and instrumental output.
ElevenLabsNewElevenLabs Music v2.5Generate music with vocals or instruments using Music v2.5, with richer arrangements and improved prompt adherence. Create a 3-second to 10-minute track from a prompt or a structured composition plan.
ElevenLabsNewElevenLabs Scribe v2ElevenLabs' Scribe v2 transcription model with key term biasing for improved accuracy on domain-specific vocabulary.
ElevenLabsNewElevenLabs Scribe v2 MedicalTranscribe medical terminology and clinical dictation with Scribe v2 Medical in 90+ languages. Supports speaker diarization and vocabulary hints. Do not upload protected health information without an approved compliance arrangement; model availability alone does not make this app HIPAA-compliant.
ElevenLabsElevenLabs Scribe v2 RealtimeTranscribe an uploaded audio clip through ElevenLabs' real-time Scribe WebSocket model. Supports 90+ languages and vocabulary hints. ArtEmotion returns the completed transcript; this is not a live microphone session. Maximum clip length: 10 minutes.
ElevenLabsNewElevenLabs Sound Effects v2Generate high-quality sound effects from text descriptions using ElevenLabs' latest sound effects model.
ElevenLabsNewElevenLabs Speech to Text (Scribe v2)Transcribe audio files with speaker diarization and audio event tagging using ElevenLabs' speech-to-text model.Stable Audio
Stability AI · 8 models
Stability AINewStable Audio 3Generate high-quality stereo music and audio up to 380 seconds from text prompts using Stability AI's Stable Audio 3 Medium — trained on licensed data for commercial use.
Stability AINewStable Audio 3 BaseThe full Stable Audio 3 Medium base checkpoint for more deliberate, higher-step music generation.
Stability AINewStable Audio 3 Base ExtendHigher-step continuation before or after an existing track.
Stability AINewStable Audio 3 Base InpaintHigher-step replacement of a selected audio section.
Stability AINewStable Audio 3 Base RestyleHigher-step Stable Audio 3 restyling with detailed prompt control.
Stability AINewStable Audio 3 ExtendContinue a track before or after its current boundaries while preserving its musical identity.
Stability AINewStable Audio 3 InpaintReplace a selected time range while matching the surrounding track.
Stability AINewStable Audio 3 RestyleTransform an uploaded track while preserving as much of its structure as you choose.Mirelo
Mirelo · 7 models
MireloNewMirelo SFX (Video → Audio)Mirelo SFX v1 video-to-audio — analyses visuals and returns a matching audio file you can layer onto the original video.MireloMirelo SFX (Video → Video)Mirelo SFX v1 video-to-video — analyses the visuals and generates matching sound effects baked directly into the output video.MireloNewMirelo SFX v1.5 (Video → Audio)Mirelo SFX v1.5 video-to-audio — improved generation quality with a start-offset option for precise audio timing control.
MireloNewMirelo SFX v1.6 (Audio Extend)Extend an existing audio clip forward in time, preserving timbre, rhythm, and tail using Mirelo SFX v1.6.
MireloNewMirelo SFX v1.6 (Audio Inpaint)Replace a section of an existing audio clip with AI-generated SFX that matches the surrounding context.
MireloNewMirelo SFX v1.6 (Text → Audio)Generate high-quality sound effects from text descriptions using Mirelo SFX v1.6. Supports looping ambience generation.MireloNewMirelo SFX v1.6 (Video → Video)Mirelo SFX v1.6 video-to-video — richer, higher-fidelity sound effects baked into output video with extended duration support via sliding-window generation.
MireloNewMirelo SFX v1.6 (Audio Extend)Extend an existing audio clip forward in time, preserving timbre, rhythm, and tail using Mirelo SFX v1.6.MireloNewMirelo SFX v1.6 (Audio Inpaint)Replace a section of an existing audio clip with AI-generated SFX that matches the surrounding context.MireloNewMirelo SFX v1.6 (Text → Audio)Generate high-quality sound effects from text descriptions using Mirelo SFX v1.6. Supports looping ambience generation.MireloNewMirelo SFX v1.6 (Video → Video)Mirelo SFX v1.6 video-to-video — richer, higher-fidelity sound effects baked into output video with extended duration support via sliding-window generation.CassetteAI
CassetteAI · 2 models
CassetteAINewCassetteAI Music GeneratorGenerate professional-quality 44.1 kHz stereo music from a text prompt using CassetteAI — a 30-second sample in under 2 seconds.CassetteAINewCassetteAI Sound EffectsCassetteAI Sound Effects — automatically analyses a scene and generates contextually appropriate sound effects without needing a text prompt.Lyria
Google · 2 models
SAM Audio
Meta · 2 models
MetaNewSAM Audio (Isolation)SAM Audio visual separation — isolates a specific sound source from background audio in a video, returning both tracks separately.
MetaNewSAM Audio (Text Separation)Isolate a specific sound from any audio file using a text prompt. SAM Audio returns both the isolated target track and the residual (everything else).
MetaNewSAM Audio (Text Separation)Isolate a specific sound from any audio file using a text prompt. SAM Audio returns both the isolated target track and the residual (everything else).Cohere
Cohere · 1 model
Hunyuan Video
Tencent · 1 model
MiniMax
MiniMax · 1 model
MMAudio
MMAudio · 1 model
PixVerse
PixVerse · 1 model
ThinkSound
ThinkSound · 1 model
Whisper
OpenAI · 1 model
