> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.jambonz.org/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.jambonz.org/_mcp/server.

#### 11.1.16

jambonz Commercial 11.1.16

**11.1.16** covers 11.1.13 through 11.1.16. It adds a preview of jambonz's own turn detection and
interrupt prediction models for the agent verb as an alternative to Krisp, ai-coustics noise isolation and
VAD, Phonic for text-to-speech and speech-to-speech, KugelAudio Fluid speech-to-speech, and
ElevenLabs Scribe v3 Live with predicted turn ends. Agent applications receive more events: whether
each `agent:update` was applied, turn-taking signals, and the end of turns the agent started
itself. The release fixes two API authorization issues, a gather inter-digit timeout bug, and a
database upgrade from 10.0.x that never completed.

#### New Features & Improvements

1. **jambonz turn detection (preview)** — the [agent](/verbs/verbs/agent) verb accepts
   `turnDetection: "jambonz"` (or `{mode: "jambonz", threshold}`), which runs jambonz's own
   end-of-turn model in the media server instead of Krisp. The default threshold is 0.9 and
   falls over 1.6 seconds of silence. This is a preview: the model and its defaults may change
   in later releases.
2. **jambonz interrupt prediction (preview)** — `bargeIn: {strategy: "interruptPrediction",
   vendor: "jambonz"}` runs jambonz's interrupt model, also a preview. The interrupt vendor must
   match the turn detection vendor; a mismatch falls back to VAD barge-in with a warning.
3. **ai-coustics noise isolation and VAD** — `aicoustics` is a noise isolation vendor
   (`noiseIsolation` on the [agent](/verbs/verbs/agent) and [config](/verbs/verbs/config)
   verbs) and a VAD vendor, with native 8 kHz and 16 kHz models. Self-hosted systems need an
   ai-coustics license key.
4. **Phonic** — `phonic` is a text-to-speech vendor for `say` (no streaming) and a
   speech-to-speech vendor for the [llm](/verbs/verbs/llm) verb, with `phonic` speech
   credentials and `phonic_s2s` LLM credentials in the portal and API. See
   [Phonic](/guides/features/tts-vendor-settings/phonic).
5. **KugelAudio Fluid speech-to-speech** — `kugelaudio` is a speech-to-speech vendor for the
   [llm](/verbs/verbs/llm) verb. Without `auth` on the verb, the account's `kugelaudio_s2s`
   credential is used, and its region (`global`, `eu`, `us`) picks the host.
6. **ElevenLabs Scribe v3 Live** — `scribe_v3_live` is available as an ElevenLabs speech-to-text
   model. With the [agent](/verbs/verbs/agent) verb it defaults to the `turn_prediction` commit
   strategy and ends the caller's turn on each commit, about 0.8 seconds sooner than VAD on a
   complete question.
7. **Agent update results** — every `agent:update` now sends an `agent_update` event to the
   eventHook saying whether it was applied, and why not when it was rejected.
8. **Turn-taking events** — the agent eventHook now receives `overlapping_speech`,
   `user_interruption` (with its cause), `interrupt_prediction_ignored`, `no_response_timeout`
   and `llm_error`, which were previously only in feature-server logs.
9. **Agent-started turns** — a turn the agent started itself (the greeting, or a reply it was
   asked to generate) now sends `turn_end` with its response and `agent_initiated: true`.
10. **Billing** — account users on a paid plan can update their card from the Billing
    overview (jambonz.cloud).

#### Changes in Behavior

1. **OpenAI Realtime default model** — an [llm](/verbs/verbs/llm) verb with `vendor: openai`
   and no `model` now uses `gpt-realtime-2.1`. OpenAI retires `gpt-realtime` on 2027-01-20.
   `vendor: microsoft` keeps `gpt-realtime`, since there the model is the Azure deployment
   name.
2. **Gather inter-digit timeout** — in [gather](/verbs/verbs/gather), the first key now stops the
   no-input timeout and starts `interDigitTimeout`. `minDigits` (else `numDigits`) only decides
   whether the entry counts; below it the result is a timeout, and the timeout actionHook
   carries the digits entered. `interDigitTimeout` now works without `minDigits`.
3. **Credential labels** — a speech or LLM credential label needs to be unique only within an
   account and vendor; a label on a sibling account no longer blocks it.
4. **Free trials** — on jambonz.cloud one free trial is allowed per mailbox: `+tag` aliases,
   and dots in Gmail addresses, count as the same address.

#### Security Fixes

* **API authorization** — `/v1/login` gave some account users a wider scope than their
  account. It now derives scope the same way as `/signin` and API keys.
* **View-only users** — a view-only user who signed in to the portal with email and password
  could make changes. View-only is now enforced for every sign-in method.
* **Query parameters** — object-valued query parameters and request fields are now treated as
  plain strings in database queries, so they can no longer widen a query across tenants.
  Self-hosted 500 responses no longer include internal error details.

#### Bug Fixes

* **Database upgrade from 10.0.x** — upgrading a 10.0.x database to 11.1.x never completed
  because the `krisp_usage` and `llm_credentials` tables were skipped. They are now created
  whenever they are missing.
* **Agent tools updates** — `update_tools` no longer removes the agent's handoff and hangup
  tools.
* **Acoustic turn detection** — with Krisp or jambonz turn detection and a speech-to-text vendor
  that sends no speech start (Deepgram), the LLM sometimes received only part of what the
  caller said. The whole turn is now kept.
* **Speech-to-text restarts** — a transcription that the vendor closed (Google's 305-second
  limit) is restarted; a restart that fails is now reported to the application as an ASR error
  instead of stopping silently.
* **Answering machine detection** — three voicemail greeting phrases that were detected as a
  human (`record your message`, `telephone number and your message`, `número de teléfono`)
  are now built-in AMD hints.
* **OAuth sign-in** — a GitHub or Google sign-in that matches no user now shows why on the
  login page, naming the verified address, instead of sending the person to sign up for a
  trial. An invited user is no longer signed in to a trial of their own.
* **Grafana dashboards** — on AWS mini, medium and large images since 11.1.6, every panel of the
  Jambonz Metrics dashboard showed `Datasource ... was not found`. The dashboards now use the
  provisioned InfluxDB datasource.
* **Websocket reconnects** — an unanswered `session:reconnect` no longer produces unhandled
  rejection log errors.
* **SIP** — a pending NOTIFY is no longer answered with 500 when a BYE ends the dialog, TCP 2xx
  responses are retransmitted until the ACK arrives, and stale TLS errors no longer affect new
  connections.

#### Upgrading

There are no database schema changes since 11.1.12.

#### Component Versions

| Component            | 11.1.12            | 11.1.16                              |
| -------------------- | ------------------ | ------------------------------------ |
| jambonz              | 11.1.12            | **11.1.16**                          |
| mediajam             | 0.5.21             | **0.5.22** (0.5.23 on Azure and GCP) |
| drachtio             | 10.1.12            | **10.1.14**                          |
| rtpengine            | 14.1.1.8-jambonz14 | **14.1.1.8-jambonz15**               |
| jambonz OSS (sbc-\*) | 0.9.15             | 0.9.15                               |
| upload-recordings    | 1.9.3              | 1.9.3                                |
| monitoring-agent     | 10.2.2             | 10.2.2                               |
| pcap-server          | 1.0.5              | 1.0.5                                |
| heplify-server       | 1.0.5              | 1.0.5                                |

#### Availability

**self-hosted on AWS** - available now: CloudFormation templates and public AMIs for all nine
server types in 30 regions, amd64 and arm64.

**self-hosted on Azure** - available now: Terraform modules and Compute Gallery images for all
nine server types, amd64 in 30 regions and arm64 in 29.

**self-hosted on GCP** - available now: Terraform modules and public images for all nine server
types, amd64 and arm64. GCP images are global, so there is no per-region list.

The Azure and GCP images ship mediajam 0.5.23, which fixes a crash at startup when the optional
jambonz turn-taking models are not installed.