SpeechGPT vs Google Flow Music (formerly Riffusion)

SpeechGPT lets you hold voice conversations in the browser using your own OpenAI API key. You type or record messages, send them through a chat interface, and hear spoken replies without installing desktop software.

Unlike hosted TTS services that bundle model costs into a subscription, SpeechGPT runs in the browser and bills you only through the OpenAI, Azure Speech Services, or Amazon Polly accounts you connect. That makes it a lightweight option for developers and language learners who already have API access and want a simple voice chat front end.

The interface supports English, Spanish, and Chinese UI labels, includes a record button for speech input, and stores session data locally in the browser. It suits developers testing voice chat flows, language learners practicing spoken prompts, and anyone who wants a minimal ChatGPT voice client on mobile or desktop.

Google Flow Music lets you create full-length songs, remix tracks, and publish music through a conversational studio built on Google's Lyria 3.5 model. riffusion.com now redirects to flowmusic.app, where you chat with Producer like you are in a session, iterate on vocals and arrangement, and export finished tracks.

Unlike one-shot music generators that spit out a clip and stop, Flow Music focuses on iterative editing. Replace and Extend let you swap specific sections or continue a song past its endpoint without regenerating the whole track. You can also direct Veo-powered music videos, split stems, apply audio effects, and vibe-code custom instruments or mini apps inside Spaces.

The free tier includes daily top-up credits and two concurrent generations with no credit card required. Paid plans raise monthly credits, concurrent generation limits, and add member perks. Google acquired the Riffusion team in 2026 and folded the product into Google Labs alongside Lyria and Veo.