v0.55.1
invoke-ai/InvokeAIv0.55.1Oct 2, 2026by github-actions[bot]
Upgrading?
AI Summary
This patch release optimizes the Deepgram Aura TTS for the Pipecat bot example, significantly reducing time-to-first audio and latency. It also fixes a critical bug in pause-mode barge-in logic where bot audio was incorrectly dropped after resolving a pause arbitration.
Key Highlights
- Deepgram Aura TTS becomes the default provider for `examples/pipecat-bot-py`, improving TTFB and reducing PSTN call latency.
- Pause-mode barge-in logic fixed to prevent bot audio drops after resolving disputes (reject, confirm, or timeout).
- Performance measurements show median gaps reduced from 1.95s to 1.01s on PSTN calls.
- Config option `BOT_TTS_PROVIDER` remains available for switching back to OpenAI TTS.
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
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Reverse engineer anything with agents, from app behavior down to native binaries.
The open source coding agent.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.