release
GPT Transcribe becomes default speech-to-text model for Lovable app AI features
docs.lovable.devagent
OpenAI's GPT Transcribe (openai/gpt-transcribe) is now available for apps, accepting audio files up to 25 MB with support for context hints, expected keywords, and language specifications for specialized vocabulary. It replaces the previous default for speech-to-text capabilities.
Stacks this affects
Lovable ships in 1 tested stack here.
More Lovable
featureLlamaParse Platform and n8n connectors enable document parsing and workflow automation in appsreleaseLovable apps can now use Seedream 5 Pro for image generation and Seedance 2.5 for video synthesisfeatureLovable now writes and runs tests for rule changes in appsfeatureLovable apps gain OIDC authentication support for enterprise SSOfeatureGPT Transcribe becomes available for speech-to-text in Lovable apps