v0.55.1
emscripten-core/emscriptenv0.55.1Oct 2, 2026by github-actions[bot]
Upgrading?
AI Summary
Default Text-to-Speech provider switched to Deepgram Aura for faster performance, along with a fix for pause-mode barge-in dropping audio.
Key Highlights
- Default TTS provider changed to Deepgram Aura (median 0.52s vs 0.94s)
- Pause-mode barge-in fix prevents bot audio from being dropped after resolution
- OpenAI `gpt-4o-mini-tts` remains available but with a new `BOT_TTS_MODEL` setting
New Features
- Configuration setting `BOT_TTS_PROVIDER` defaults to `deepgram`
- Configuration setting `BOT_TTS_MODEL` defaults to `tts-1` for OpenAI
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
ggml-org/llama.cpp★ 131,960
LLM inference in C/C++
LadybirdBrowser/ladybird★ 66,608
Truly independent web browser
ClickHouse/ClickHouse★ 50,532
ClickHouse® is a real-time analytics database management system
LizardByte/Sunshine★ 42,493
Self-hosted game stream host for Moonlight.
deskflow/deskflow★ 29,987
Share a single keyboard and mouse between multiple computers.