chatterbox-tts-api and openai-edge-tts
These are complementary tools: chatterbox-tts-api provides local voice cloning capabilities while openai-edge-tts offers a free cloud-based alternative, allowing users to choose between on-device synthesis or external endpoints depending on their latency, privacy, and voice customization requirements.
About chatterbox-tts-api
travisvn/chatterbox-tts-api
Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)
Built on FastAPI with async processing, the API wraps Chatterbox TTS to support 22 languages with multilingual voice cloning, automatic text chunking for long inputs, and real-time memory management. Includes an optional React frontend with voice library management, a bundled voice sample for quick testing, and Docker profiles for CPU/GPU/Blackwell deployments with persistent voice storage.
About openai-edge-tts
travisvn/openai-edge-tts
Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs
Leverages Microsoft Edge's native TTS service via `edge-tts` for zero-cost synthesis, supporting Server-Sent Events streaming and flexible audio formats (mp3, opus, aac, flac, wav, pcm) with adjustable playback speeds. Provides optional direct voice selection from the full `edge-tts` catalog or OpenAI voice mappings, plus optional ffmpeg integration for format conversion. Containerized with Docker for single-command deployment.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work