AI Audio

Local desktop studio for zero-shot cloning, dictation, and cinematic dubbing (646 languages)

Local AI audiobook studio with per-sentence emotion/voice control

Local-first voice cloning studio with multi-engine TTS + timeline

Local voice AI runtime: ASR, diarization, TTS, cloning + OpenAI-compatible API

Full-duplex, multi-agent, 100% local conversational voice engine

JUCE synth that uses diffusion models as oscillators

Code-first procedural SFX with MCP natural-language tools

One-command CLI for SFX, loops, songs, narration via ComfyUI

AI sample-library manager + generative “chaos mixer”

One-file Windows app for Stable Audio Open with 217 presets

Tiny ~82M Apache-2.0 TTS with strong English quality

Multilingual TTS with short-clip cloning

Open multilingual TTS + cloning from ~3s audio

Zero-shot voice cloning TTS

MIT-licensed multilingual voice cloning

Fast real-time multilingual TTS (MyShell)

Expressive TTS with emotion tags

Style-controllable TTS

Expressive TTS with non-speech sounds (laughter, etc.)

Few-shot voice cloning / conversion pipeline

Retrieval-based voice conversion

Ultra-low-latency cloud TTS (40+ languages)

TTS optimized for live voice agents + cloning

Emotionally controllable speech / empathic voice

On-prem / controlled-deployment TTS for CX

Character / interactive realtime voices

AI music with clean stem + Ableton project export

AI MIDI generator as VST3/AU/AAX for DAWs

Real-time SFX / Foley / ambience creator (VST/AU)

AI music generator; strong instrumental/mastering sound

Offline AI loop/texture VST (Stable Audio engines)

On-device Mac audio cleaner (noise, fillers, EQ)

Offline cleaner/master for Suno/Udio artifacts

Local GPU app: stems → MIDI → generation → mix

Browser/native DAW with AI gen + timeline Copilot

AI denoise/stem + DSP rack as VST3/AU/LV2

Lightweight offline TTS (rhasspy)

Alibaba open TTS with zero-shot cloning

Text-to-audio / music from Stability AI

Cloud TTS, cloning, agents, dubbing

Open-source AI music suite with layer/LEGO pipelines, cover, repaint, stems — local Suno/Udio alternative

Leading consumer AI music generator (full songs from prompts)

Expressive TTS/voice cloning with inline emotion tags; API-first

Open-source multilingual voice cloning TTS (Resemble AI)

AI voiceover studio with video timeline sync aimed at e-learning and YouTube

Enterprise-grade AI narration voices

Text-based audio/video editor with Overdub, Studio Sound, and screen recording

Licensed music + SFX + footage library with expanding AI tools

Browser podcast studio with AI enhancement and hosting

Open TTS model noted for high-fidelity (~44kHz) output

Open multi-speaker dialogue TTS with laughs/pauses

Conversational Speech Model for emotional expressiveness

OSS TTS optimized for conversational/chatbot prosody

Compact bilingual EN/ZH 0.5B TTS with prompt control

ByteDance scene audio: dialogue+SFX+ambience+music one pass

Open multimodal audio generation synced to video

CSS-like language binding sounds to UI events

AI music generation often A/B'd with Suno

AI royalty-free music tailored for videos/podcasts

AI music generator with editable structure

Stem splitter for vocals/instruments

AI stem separation + practice tools

AI filler-word/noise cleaner for voiceovers

Automated loudness leveling and podcast/audio mastering

AI noise cancellation for calls, research, and voice notes

Browser AI audio cleanup (Enhance Speech) often used alongside photo/video creator stacks

Developer-oriented AI TTS/voice API often used for product narration and apps