Find a free alternative.

Voicebox

Local-first voice synthesis studio for text-to-speech and voice cloning with downloadable model engines.

OpenVoice

Open-source instant voice-cloning toolkit that can create speech in a cloned voice from short reference audio. It is a technical component, not a complete hosted TTS service.

MuseTalk

Open-source audio-driven talking-face and lip-sync model for animating a portrait. It covers the avatar-animation feature, not a complete hosted video-creation platform.

LiveTalking

Open-source real-time digital-human streaming system with audio/video synchronization, voice options, and avatar models. It requires technical setup and is not a hosted creator SaaS.

Cherry Studio

Desktop multi-model AI workspace with chat and agents; model access may require a paid API, a free provider tier, or local hardware.

Chat UI

Self-hostable chat interface for model providers. This links to the software repository, not a hosted free-chat service; configure your own model backend.

Open Notebook

Self-hosted research notebook for documents and cited answers; connect a model provider or run a local model.

Kotaemon

Open-source document RAG app for asking questions about your own files; configure an LLM and embeddings backend.