@cloudflare/voice-assemblyai@0.1.0

cloudflare/agents@cloudflare/voice-assemblyai@0.1.0Aug 27, 2026by ben-reitz

AI Summary

Minor update aligning with the main voice package improvements to lifecycle accuracy and diagnostics.

Key Highlights

Clears stale interim transcripts during call lifecycle events.
Emitting `speaking` status only when the first server audio chunk is sent.
Structured diagnostics and error logging.
Preserved model finish reasons and typed per-turn timing.

New Features

Improved voice lifecycle accuracy.
Enhanced diagnostics without reading arbitrary provider response bodies.

Full Release Notes


### Minor Changes

- [#2157](https://github.com/cloudflare/agents/pull/2157) [`f08ee06`](https://github.com/cloudflare/agents/commit/f08ee06fd610756de0d8abf539dfe9b746bdd7c5) Thanks [@cjol](https://github.com/cjol)! - Improve voice lifecycle accuracy, diagnostics, and per-turn timing visibility.

  - Clear stale interim transcripts when calls start, end, disconnect, close, or fail during startup.
  - Emit `speaking` only when the first server audio chunk is sent.
  - Add structured, content-free browser diagnostics and structured Worker error logging without reading arbitrary provider response bodies.
  - Report transcriber startup and runtime failures through `onFatalError`, structured client errors, and reliable call cleanup.
  - Preserve model finish reasons and distinguish no-output, output-limit, content-filtered, and model-error completions.
  - Add stable typed per-turn timing summaries for speech, text, terminal outcomes, model streaming, reasoning exposed by the model stream, and overlapping TTS work through `VoiceClient` and the React hooks.
  - Keep the existing four-field metrics wire shape compatible while making no-audio and streamed TTS accounting consistent.
  - Update the bundled voice providers to propagate lifecycle failures and log errors consistently.