AI Audio

Free, open-source desktop app for running and training AI models on local hardware, with local LLM, diffusion image/video, MLX, GGUF, audio, agent-tool, and model-serving workflows across macOS, Windows, and Linux.

Open-source, local-first desktop voice AI studio for voice cloning, voice design, video dubbing, transcription, dictation, and audiobook creation, with a 646-language catalog and downloadable builds for macOS, Windows, and Linux.

Soniox TTS v2 is a multilingual text-to-speech API that generates natural, expressive speech in 60+ languages with programmable emotion tags, voice cloning, automatic language mixing, and low-latency streaming — priced at $0.70 per generated hour. It targets voice agents, dubbing, IVR, and audiobook workloads that need one model with a consistent voice identity across languages.

Cross-platform local speech-to-text inference library built on ggml. It supports 16+ ASR model families and 60+ variants with streaming and batch transcription plus Metal, Vulkan, CUDA, and TinyBLAS acceleration.

ByteDance Seed's end-to-end AI audio creation model jointly generates dialogue, sound effects, and ambience in one scene. It supports timeline-controlled generation, reference-audio conditioning, roughly two-minute audio extension, and natural output in 20+ languages.

AI phone receptionist for small businesses that answers calls, books meetings, qualifies leads, and handles follow-up questions with natural conversational voice — no code setup required.

Leading AI music generator that creates complete songs with vocals, lyrics, and full production from text prompts. Includes Suno Studio DAW, stem separation, and commercial licensing on paid plans.

Free open-source, privacy-first voice input app for macOS — press Control, speak, and your transcribed text is pasted instantly into any application, all running locally.

Multi-modal AI platform by Step Intelligence with real-time voice interaction, paralinguistic awareness, image generation, and lightning-fast speech recognition.

Browser-based collaborative music creation platform with AI sous-chef co-producer. Record ideas, layer sounds, collaborate live, and share tracks on an infinite canvas.

Chinese AI platform offering 600+ voice models with Speech 2.8 Turbo, multimodal chat, and video generation capabilities. Industry-leading text-to-speech quality.

AI music generation platform by Stability AI. Create professional-quality songs up to 6 minutes long with multiple model sizes for different deployment needs.

AI meeting note taker for live transcription, automated summaries, action items, and team collaboration.

AI meeting assistant for recording, transcribing, summarizing, and searching conversations.

AI audio and video editor for podcasts, screen recordings, transcription, clips, and studio-quality production.

AI audio platform for realistic text-to-speech, voice cloning, dubbing, and speech generation.