ChatTTS vs Audio.co (formerly RadioNewsAI)

ChatTTS is an open-source text-to-speech model built for dialogue. The 2Noise team trained it on over 100,000 hours of Chinese and English speech so it sounds natural in back-and-forth conversation, not just scripted narration.

What sets it apart is prosody control at a granular level. The model can layer in laughter, pauses, and interjections, and it handles multiple speakers in a single session. That makes it a fit for LLM assistants, conversational audio, and dialogue-heavy multimedia.

Developers install it via pip or clone the GitHub repo. The open-source release on Hugging Face is a 40,000-hour base model under AGPLv3+. The team positions it for research and dialogue use cases, with contact at [email protected] for roadmap questions.

Audio.co is Aiir's broadcast audio platform for creating ready-to-air content for radio stations and podcasts. From one dashboard, stations can produce newscasts, commercial spots, weather reports, and traffic updates, all voiced and formatted for on-air use. Plans start at $19 per month.

The news module pulls stories from websites or RSS feeds and rewrites them with scripting models trained on your station's style. When sources publish new content, scheduled newscasts refresh automatically, with finished files delivered via download link, Dropbox, or FTP to your playout system.

Ad production is built for quick spec spots and full campaigns. Describe a client's business, pick an AI voice or clone a permitted talent, and Audio.co pairs the script with a music bed from TM Studios' production library before assembling the finished commercial.

Weather and traffic round out the toolkit. Forecasts use WeatherAPI data with support for postal codes, ZIP codes, or latitude and longitude coordinates. Traffic reports cover a defined area with customizable incident counts and pronunciation rules for local road names.