Engineering notes and product updates from the jambonz team.https://jambonz.orghttps://jambonz.org/blog/getting-started-with-the-jambonz-python-sdkhttps://jambonz.org/blog/getting-started-with-the-jambonz-python-sdkThe AI dev community runs on Python — so we built a Python SDK for jambonz. A tour of the verbs, plus a webhook IVR and a WebSocket voice AI agent.Mon, 29 Jun 2026 00:00:00 GMThttps://jambonz.org/blog/how-to-stream-text-from-llms-using-jambonzhttps://jambonz.org/blog/how-to-stream-text-from-llms-using-jambonzA deep dive on jambonz LLM and TTS streaming for low-latency Voice AI — the websocket protocol, the say verb, the Node.js SDK, and a full Anthropic example app.Sat, 21 Dec 2024 00:00:00 GMThttps://jambonz.org/blog/microsoft-teams-direct-routing-with-jambonzhttps://jambonz.org/blog/microsoft-teams-direct-routing-with-jambonzHow SoundOfData and Callable.io set up jambonz as a Direct Routing SBC for Microsoft Teams — drachtio TLS, jambonz settings, and Microsoft 365 carrier and customer tenant configuration.Mon, 14 Oct 2024 00:00:00 GMThttps://jambonz.org/blog/some-initial-thoughts-on-openais-realtime-apihttps://jambonz.org/blog/some-initial-thoughts-on-openais-realtime-apiI added OpenAI's Realtime API to jambonz, then ran the caller's audio through Deepgram in parallel to compare accuracy and latency — and what that reveals about speech-to-speech vs. traditional ASR pipelines.Mon, 07 Oct 2024 00:00:00 GMThttps://jambonz.org/blog/text-to-speech-latency-the-jambonz-leaderboardhttps://jambonz.org/blog/text-to-speech-latency-the-jambonz-leaderboardWe benchmarked time-to-first-byte across seven TTS vendors — Deepgram, ElevenLabs, Google, Microsoft, PlayHT, Rime Labs, and Whisper — for conversational AI. Here's the jambonz TTS latency leaderboard.Mon, 15 Apr 2024 00:00:00 GMThttps://jambonz.org/blog/speech-companies-are-failing-at-conversational-aihttps://jambonz.org/blog/speech-companies-are-failing-at-conversational-aiConversational AI has unique needs that long-form transcription doesn't — endpointing control, prompt-aware APIs, and pause/resume billing. Three features speech vendors still aren't shipping.Sat, 06 May 2023 00:00:00 GMT