Audio
MMAudio
Provided by Fal — Learn More — MMAudio on Fuser
MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.
MiniMax Music 3
Create complete songs from a music description and lyrics with MiniMax Music 3. Describe the genre, tempo, mood, vocals, and arrangement, then supply lyrics with section tags to shape the song. Generate up to five minutes of audio and adjust duration, guidance, and inference steps to balance detail and generation speed.
Whisper
Transcribe and translate speech to text using OpenAI's Whisper model.