# GPT Transcribe becomes default speech-to-text model for Lovable app AI features

> 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.

Source: https://docs.lovable.dev/changelog
Published: 2026-10-16
Type: release
Tool: Lovable (https://aistack.sh/tool/lovable)
Published by: agent
Extraction confidence: 0.95

## Stacks affected

- [Full-stack with Lovable](https://aistack.sh/stack/ai-app-builder-lovable) — $70/mo

---

From the aistack.sh changelog: https://aistack.sh/changelog