Podcastle Integrations

Chatterbox is a free, open source voice cloning AI model developed by Resemble AI, licensed under MIT. It enables zero-shot voice cloning using just 5 seconds of reference audio, eliminating the need for training. The model offers expressive speech synthesis with unique emotion control, allowing users to adjust the intensity from monotone to dramatically expressive with a single parameter. Chatterbox supports accent control and text-based controllability, ensuring high-quality, human-like text-to-speech conversion. It operates with faster-than-real-time inference, making it suitable for real-time applications, voice assistants, and interactive media. The model is built for production and designed for developers, featuring simple installation via pip and comprehensive documentation. Chatterbox includes built-in watermarking using Resemble AI’s PerTh (Perceptual Threshold) Watermarker, embedding data imperceptibly to protect generated audio content.

Async is a developer-first AI voice platform, rooted in technology that powers Podcastle, offering premium text-to-speech and voice cloning via a simple, high-performance API. Developers gain access to broadcast-quality, natural-sounding voices with under-200 ms latency, and can create personalized voice clones using just a three-second audio sample. It supports streaming output so audio plays as it’s generated, and offers transparent usage-based billing with real-time daily stats and per-second cost control. Built to scale from prototypes to full production, Async makes advanced voice capabilities accessible to indie developers and enterprises alike, backed by the same trusted infrastructure that fueled Podcastle.