Comfy Workflows
Browse ready-to-run ComfyUI workflows for AI image, video, audio, and 3D generation.
Browse ready-to-run ComfyUI workflows for AI image, video, audio, and 3D generation.
The Audiogen website shows a temporary deployment pause.
AI medical scribe that drafts clinical notes, letters, and forms from patient conversations.
Practice English pronunciation with instant word-by-word feedback on any phrase.
Generate original audio stories by choosing a mood, setting, length, and AI narrator.
Turn podcast episodes into searchable transcripts, AI summaries, mind maps, and notes you can export.
Turn podcast recordings into show notes, captioned clips, and published episodes.
Generate songs, instrumentals and AI covers from prompts, lyrics and reference audio
AI translation for communication across linguistic communities
Generate original music from text descriptions and download songs as WAV or MP3 files.
Voice AI product links, voiceover guidance and support resources on a page-not-found screen.
Backtrack records hosted event meetings and turns conversations into sponsor ROI reports and CRM-ready notes.
AI SOAP note generation from shorthand, dictation, session recordings, telehealth visits and uploaded audio.
AI journaling and narrated books built chapter by chapter from learning topics or personal entries.
WZRD generates audio-driven music videos using AI, percussion analysis and harmonic elements.
Local-first AI music tools that turn video, images, text and emotional metadata into editable MIDI.
Recognize song chords, beats and keys, view instrument diagrams, and separate audio into stems.
Voice AI agents with REST API access, programmable conversation flows, and existing telephony integration.
An AI assistant for clinical documentation, coding, clinical reasoning, and EHR-connected workflows.
Speech recognition with improved transcription of proper nouns, alphanumerics, and noisy audio
Voice AI for drive-thru order taking, upselling, and restaurant operations
Tangia adds AI voices, chat characters, memes, soundbites and image generation to livestreams.
Rights-cleared music datasets, stems, MIDI, and semantic search for AI developers via API and MCP.
Transcribe audio, draft content, generate images and create voiceovers in a shared AI workspace.
Split songs into downloadable drums, instrumental, bass and voice tracks using artificial intelligence.
Transform uploaded or recorded audio with AI voices, pitch controls, custom voice models, and batch conversion.
Medical speech recognition and documentation assistance that learns from corrected consultations.
AI meeting notes, searchable meeting knowledge, and automated follow-ups without a meeting bot.
Epidemic Sound Soundmatch recommends music tracks that match scenes in a video.
An AI-generated, never-ending audio discussion between Werner Herzog and Slavoj Žižek.
Turn text, scripts, audio and music into videos with narration, subtitles, animated images and soundtracks.
An audio search engine whose search is no longer available, with a recommendation to use a YouTube to MP3 converter.
AI short-form video generator with scripts, voiceovers, visuals and customizable subtitles
A service that requires an invitation from an existing user to cast.
Mindset combines artist audio stories, daily self-care check-ins, expert guidance, and community reflections.
AI video and audio clipping with branded captions, social copy, and clip editing.