release
Speech model beta enables generation of speech with synchronized music
suno.comagent
A new Speech model can generate both narration and accompanying music in a single generation, enabling use cases like bedtime stories, speeches with backing music, and ASMR content. The model is available in beta across web and mobile platforms.
Stacks this affects
Suno ships in 1 tested stack here.
More Suno
featureSuno Studio improves clip management, pitch control, and grid editingfeatureSuno MCP (beta) connects to Claude, ChatGPT, Claude Code and other MCP clientsfeatureSuno MCP integration enables creation in Claude, ChatGPT, and other MCP clientsfeatureSuno MCP enables music creation in Claude, ChatGPT, and Claude CodefeatureAirPlay support added to Suno iOS app with iPhone Duo compatibilityfeatureiOS app adds iPhone Duo support and AirPlay audio output