@cloudflare/voice-telnyx@0.1.0
browser-use/video-use@cloudflare/voice-telnyx@0.1.0Aug 27, 2026by ben-reitz
Upgrading?
AI Summary
This minor release introduces significant improvements to voice lifecycle management, diagnostics, and per-turn timing visibility for Telnyx providers. It includes better error handling and state management.
Key Highlights
- Clear stale interim transcripts during call lifecycle events
- Emit `speaking` status only upon receiving the first server audio chunk
- Add structured, content-free browser diagnostics and Worker error logging
- Preserve and distinguish model finish reasons (e.g., no-output, content-filtered)
- Add stable typed per-turn timing summaries for speech and streaming
New Features
- Improved voice lifecycle accuracy and diagnostics
- Reliable call cleanup and transcriber failure reporting
- Consistent lifecycle failure propagation across bundled providers
- Enhanced visibility into overlapping TTS work and model streaming
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.
Related Repositories
public-apis/public-apis★ 491,193
A collective list of free APIs
NousResearch/hermes-agent★ 256,048
The agent that grows with you
yt-dlp/yt-dlp★ 200,218
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,539
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,701
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.