v0.55.1
tt-a1i/archifyv0.55.1Oct 2, 2026by github-actions[bot]
Upgrading?
AI Summary
This release improves TTS performance by defaulting the example bot to Deepgram Aura and introduces a configuration option for OpenAI TTS models. It also fixes a bug where bot audio would drop after a pause-mode barge-in resolution.
Key Highlights
- Deepgram Aura TTS now speaks by default for the example bot, offering faster time-to-first audio.
- OpenAI TTS now supports a `BOT_TTS_MODEL` setting (defaults to `tts-1`).
- Fixed pause-mode barge-in dropping bot audio after resolution.
New Features
- BOT_TTS_MODEL configuration setting
- Deepgram Aura TTS default for example bot
Full Release Notes
### Changed - **`examples/pipecat-bot-py` now speaks with Deepgram Aura TTS by default** (`BOT_TTS_PROVIDER=deepgram`), reusing the `DEEPGRAM_API_KEY` its speech-to-text already needs, and synthesizing directly at the call's 8/16 kHz. Measured on 12 requests each: time to first audio was a median of 0.52 s (worst 0.59 s), against 0.94 s with a 12.7 s worst case for OpenAI `gpt-4o-mini-tts`. On PSTN calls the median gap between the caller's last word and bot audio went from 1.95 s to 1.01 s, and a goodbye that had waited 23 s started in 0.13 s. `BOT_TTS_PROVIDER=openai` remains available, now with a `BOT_TTS_MODEL` setting that defaults to `tts-1` (median 1.64 s, worst 2.3 s) rather than the occasionally stalling `gpt-4o-mini-tts`. ### Fixed - **Pause-mode barge-in no longer drops bot audio after a resolution** ([#620](https://github.com/thevoiceguy/siphon-ai/issues/620)). Resolving a pause arbitration (reject, confirm, or either timeout) re-pushes the retained tail and the post-pause audio straight into the media engine. A WS server still streaming at real time, which is what a correctly paced server does (including `sdks/python`'s `AudioSender` and `sdks/typescript`), then accumulated behind that backlog, and the 200 ms window (PROTOCOL.md §5.5) evicted about the pause length minus 200 ms of bot speech per resolution: 158 frames over 5 rejects on a live PSTN call. The window now tolerates the backlog the daemon itself created, shrinking as it drains and resetting on every flush, so PROTOCOL.md §4.11's "playout resumes where it stopped, then any audio streamed during the pause plays behind it" holds. Over-rate servers are still bounded. No configuration or protocol change. --- **Artifacts** - Static musl binaries for `x86_64` and `aarch64` (`.tar.gz`). - Debian packages (`.deb`) for `amd64` and `arm64` — `apt install ./siphon-ai_*_amd64.deb`. - `SHA256SUMS` — verify with `sha256sum -c SHA256SUMS`. - `*-sbom.cdx.json` — CycloneDX SBOM. - `SHA256SUMS.cosign.bundle` — cosign keyless signature over the checksums. - Container: `ghcr.io/thevoiceguy/siphon-ai:v0.55.1` (multi-arch, cosign-signed). Verify the checksums signature: ``` cosign verify-blob --bundle SHA256SUMS.cosign.bundle \ --certificate-oidc-issuer https://token.actions.githubusercontent.com \ --certificate-identity-regexp 'release.yml@' SHA256SUMS ```
Related Repositories
affaan-m/ECC★ 285,767
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
react/react★ 251,624
The library for web and native user interfaces.
nodejs/node★ 122,519
Node.js JavaScript runtime ✨🐢🚀✨
Leonxlnx/taste-skill★ 100,614
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
louislam/uptime-kuma★ 92,731
A fancy self-hosted monitoring tool