v0.55.1
THU-MAIC/OpenMAICv0.55.1Oct 2, 2026by github-actions[bot]
Upgrading?
AI Summary
Optimizes the TTS experience by defaulting to Deepgram Aura for faster response times and fixes a bug where bot audio was dropped during pause-mode barge-in resolutions.
Key Highlights
- Deepgram Aura TTS becomes the default provider for the Python example bot, reducing time-to-first audio significantly.
- Pause-mode barge-in logic updated to retain and resume bot audio correctly after resolution events.
- Time-to-first audio improved from 0.94s to 0.52s median.
New Features
- Default TTS provider switched to Deepgram Aura
- Added BOT_TTS_MODEL setting for OpenAI
- Fixed audio dropout in pause arbitration
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
openclaw/openclaw★ 392,712
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,078
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 358,632
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,745
The open source coding agent.
n8n-io/n8n★ 208,266
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.