Skip to content

Megaphone

v1.0.3 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

apple apple-ai freeflow macos megaphone megaphone-tts
+5 more
speechanalyzer spokenly text-to-speech whisper whisprflow

Affected surfaces

auth

ReleasePort's take

Light signal
editorial:auto 9d

The Settings UI no longer includes the API key and provider configuration screens.

Why it matters: Removal of the API key and provider configuration UI in v1.0.3 eliminates those settings surfaces; operators must adjust workflows accordingly.

Summary

AI summary

API key and provider configuration UI removed; Megaphone is now fully on‑device.

Changes in this release

Breaking High

Removes API key and provider configuration UI from Settings.

Removes API key and provider configuration UI from Settings.

Source: llm_adapter@2026-07-17

Confidence: high

Full changelog

[1.0.3] - 2026-07-14

Removed

  • The API key and provider configuration UI is gone from Settings — Megaphone is now fully on-device end to end, with no cloud option surfaced anywhere. (The LLM cleanup layer remains dormant in the codebase for a possible on-device Apple Foundation Models port.)

Download

Megaphone.dmg — requires macOS 26 (Tahoe) on Apple silicon.

Breaking Changes

  • Removed API key and provider configuration UI from Settings.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Megaphone

Get notified when new releases ship.

Sign up free

About Megaphone

All releases →

Related context

Earlier breaking changes

  • v1.1.0 Edit Mode disabled due to retired LLM layer; setup step removed.
  • v1.1.0 Menu bar icon now hidden by default; must re‑enable in Settings.
  • v1.0.0 Renamed project from FreeFlow to Megaphone.
  • v1.0.0 Transcription runs entirely on‑device using Apple's SpeechAnalyzer; cloud transcription stack removed.

Beta — feedback welcome: [email protected]