Audio
Construct adaptable pipelines for audio transcription, voice generation, or high-quality music synthesis.
Audio show transcription
Operate Whisper on your preferred hardware, tailored with pre-processing like ffmpeg as desired. Utilize Dibtrun's map feature to activate numerous containers for parallel transcription of a single audio track.
Music composition
Host diffusion Models to create high-quality music samples from text or audio input. Serve your model in any form, including a serverless Discord bot.
Voice synthesis
Produce lifelike human speech in real-time using open-source models. Seamlessly integrate voice generation with LLM synthesis within a single application.