<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
<channel>
<title>Reecall changelog</title>
<link>https://developers.reecall.com/changelog</link>
<description>Reecall platform changes</description>
<item>
<title>Booking requests no longer fail on large Enovacom GXD5 centers</title>
<link>https://developers.reecall.com/changelog/2026-11-16-enovacom-large-config-restarts</link>
<guid>https://developers.reecall.com/changelog/2026-11-16-enovacom-large-config-restarts</guid>
<pubDate>Mon, 16 Nov 2026 00:00:00 GMT</pubDate>
<description>Since November 12, on Enovacom GXD5 centers with a very large configuration,
refreshing the copy of the center's exams, sites, rooms and practitioners could
restart the booking service, about once an hour of calls. Booking requests in
progress at that moment failed, on Enovacom and on other booking software alike.
The copy now holds only what the assistant uses, and storing or reading it no
longer takes enough memory to restart the service.</description>
</item>
<item>
<title>1.11.0</title>
<link>https://developers.reecall.com/changelog/1110</link>
<guid>https://developers.reecall.com/changelog/1110</guid>
<pubDate>Mon, 16 Nov 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

* The Reecall MCP server supplies dashboard links so connected AI agents can direct you to your Assistants and other resources.

### Bug fixes

#### Requests to repeat no longer talk over the caller

* When an Assistant cannot transcribe what a caller said while it was speaking, it waits 1.5 seconds after it finishes before it asks the caller to repeat. If the caller speaks during that time, the Assistant does not ask.
* The caller can interrupt the request to repeat, even when `disableInterruptions` is `true`. The Assistant does not ask again until it transcribes the caller's speech. Before, with `disableInterruptions`, the request could repeat several times in a row.</description>
</item>
<item>
<title>Exam order kept across days</title>
<link>https://developers.reecall.com/changelog/2026-11-13-multi-exam-order-across-days</link>
<guid>https://developers.reecall.com/changelog/2026-11-13-multi-exam-order-across-days</guid>
<pubDate>Fri, 13 Nov 2026 00:00:00 GMT</pubDate>
<description>When a caller books several exams, the exam order set in the booking
configuration now also holds across days. An exam set to pass first is never
booked on a later day than the exam that follows it. Before, the order only
applied to exams on the same day. This covers the order per exam category and
the order rules per exam.

If the order rules form a loop, such as A before B, B before C and C before A,
no booking can respect them. The assistant then offers no slot and transfers the
call.</description>
</item>
<item>
<title>1.10.0</title>
<link>https://developers.reecall.com/changelog/1100</link>
<guid>https://developers.reecall.com/changelog/1100</guid>
<pubDate>Fri, 30 Oct 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### New features

#### Email tool

* Added `send_email` so your Assistant can email configured recipients during a call, such as notifying the front desk that a caller will be late. See [Email tool](/docs/send-email).

### Improvements

* Faster first reply on calls that use a Mistral model.
* Post-call data extraction retries stalled requests, reducing calls without extracted data.

### Bug fixes

* `resolve_datetime` counts `days_from_now` in calendar days in the Assistant's time zone. Tomorrow is `1`, even when it is less than 24 hours away.
* When a transfer destination is missing, the Assistant picks one of your configured destinations before announcing the transfer. This prevents an announcement followed by a failure.

## Data API

### Improvements to Mapper feature

* The `date` helper reads day-first dates (`01/03/2024` is March 1) and Excel serial numbers. A date it cannot read now fails the row instead of being read month first. For month-first files, use the new `parse_date` helper: `{{ Date | parse_date('MM/dd/yyyy') | date('yyyy-MM-dd') }}`
* `POST /automation/mappers/{id}/run` returns a `400` with `BAD_INPUT` for a malformed body, instead of a `500`.
* Saving a mapper validates `inputOptions`.
* A JSON source made of one object that wraps the rows, such as `{ "items": [...] }`, is rejected instead of being read as one row.</description>
</item>
<item>
<title>1.9.1</title>
<link>https://developers.reecall.com/changelog/190</link>
<guid>https://developers.reecall.com/changelog/190</guid>
<pubDate>Wed, 28 Oct 2026 00:00:00 GMT</pubDate>
<description>## Data API

### Breaking changes

#### Blueprint `type` is now required

* Blueprints require a `type`: `assistant`, `mapper`, or `automation`.
* The `type` must match the models the Blueprint creates. A Blueprint whose models don't match its `type` is rejected.
* Existing Blueprints have been given the `type` that matches their models.
* If you create Blueprints through the API, add `type` to your requests.

### Security

#### Blueprint access between projects

* Fixed access to Blueprints from other projects through a project-scoped API key. Each key only sees Blueprints from its own project.

## AI Assistants

### New features

#### Transfer a call to another Assistant

* Added `transfer_to_assistant` so your Assistant can hand a conversation to another Assistant in the same organization and project without ending the call. See [Assistant transfer tool](/docs/transfer-to-assistant).

#### Date and time resolution tool

* Added `resolve_datetime` so an Assistant can look up a date's day of the week and distance from the current date during a conversation. See [Date and time tool](/docs/resolve-datetime).

### Fixes

#### Transfer summaries in the Assistant's language

* The `conversationSummary` sent with a WebRTC transfer is written in the Assistant's language.</description>
</item>
<item>
<title>1.8.0</title>
<link>https://developers.reecall.com/changelog/180</link>
<guid>https://developers.reecall.com/changelog/180</guid>
<pubDate>Thu, 08 Oct 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### New features

#### Send an SMS during a conversation

* Added `send_message` so your Assistant can send an SMS to the caller or another number during a conversation.
* Configure each tool with a message template, sender name, and the details the Assistant must collect to fill it in, such as a date, time, or reference.
* Use variables and injected data in the text, such as the caller's name.
* The collected details are checked against your rules before the SMS is sent.
* On WebRTC calls or when the caller's number is hidden, the Assistant asks which number to send the SMS to.

See [SMS tool](/docs/send-message).

### Improvements

#### Tool names

* Tool names in `nameOverride` must be unique on an Assistant and contain only letters, digits, `_`, and `-`, up to 64 characters.</description>
</item>
<item>
<title>1.7.1</title>
<link>https://developers.reecall.com/changelog/171</link>
<guid>https://developers.reecall.com/changelog/171</guid>
<pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

#### Stable session ID for MCP servers

* The `X-session-id` header sent to MCP servers carries the conversation's `traceId` instead of a random value.

#### Wider speech speed range for Gradium voices

* The `tts.speed` setting covers Gradium's full speed range. `-1` is slower and `1` is faster than before. See [TTS settings](/docs/tts-settings).
* `0` or `null` keeps the same pace as before, so Assistants that don't set a speed are unaffected.

### Fixes

#### Transfer reason on WebRTC transfers

* Fixed the missing `reason` field in the `RequestTransfer` RPC payload sent to WebRTC clients.

#### Conversation summary on WebRTC transfers with STS models

* Fixed missing `conversationSummary` values in WebRTC transfers from speech-to-speech Assistants.</description>
</item>
<item>
<title>1.7.0</title>
<link>https://developers.reecall.com/changelog/170</link>
<guid>https://developers.reecall.com/changelog/170</guid>
<pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### New models

#### Language models

- **GPT-5.6 Sol**, **GPT-5.6 Terra**, and **GPT-5.6 Luna** from OpenAI are available.
- **Claude Haiku 4.5** from Anthropic is available.
- **Gemini 3.8 Flash** and **Gemini 3.5 Flash-Lite** from Google are available.

#### Speech-to-speech models

- **GPT-Realtime 2.1** and **GPT-Realtime 2.1 Mini** from OpenAI are available, with stronger tool calling and more reliable interruption handling.
- **Gemini 3.8 Live** from Google is available as the stable successor to Gemini 3.1 Flash Live.

#### Speech-to-text models

- **Universal-3.5 Pro Realtime** from AssemblyAI is available and recommended.

#### Text-to-speech models

- **Cartesia Sonic-3.5** is available as the drop-in successor to Sonic-3.

### Improvements

#### Speech speed in Advanced Settings

- Set `tts.speed` to control Assistant speech speed from `-1`, the slowest, to `1`, the fastest. `0` or `null` keeps the integration's normal pace. See [TTS settings](/docs/tts-settings).

#### Noise cancellation in Advanced Settings

- Set `audio.noiseCancellation` to choose the caller's audio filter: `bvc_telephony`, the default, `bvc`, `nc`, or `disabled`. It applies to both LLM + TTS + STT and STS Assistants. See [Audio settings](/docs/audio-settings).

#### Model lifecycle metadata

- Model catalogue entries expose `deprecation` and `discontinuation` in their `metadata`, each with a `date` and, when available, the `fallback` model ID to migrate to.
- The portal prevents selecting models whose discontinuation date has passed.

### Deprecations and discontinuations

The following models are flagged as deprecated or discontinued by their provider.

| Type | Model                                                           | Status          | Date       |
| ---- | --------------------------------------------------------------- | --------------- | ---------- |
| TTS  | `eleven_turbo_v2_5`                                             | Deprecated      | \-         |
| TTS  | `gemini-2.5-flash-tts`                                          | Deprecated      | \-         |
| STS  | `openai-realtime/gpt-realtime`                                  | Discontinuation | 2027-01-20 |
| STS  | `openai-realtime/gpt-realtime-mini`                             | Discontinuation | 2027-01-20 |
| STS  | `gemini-realtime/gemini-2.5-flash-native-audio-preview-12-2025` | Deprecated      | \-         |</description>
</item>
<item>
<title>1.6.1</title>
<link>https://developers.reecall.com/changelog/161</link>
<guid>https://developers.reecall.com/changelog/161</guid>
<pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

#### Advanced Settings with STS models

- Added `stt` and `vad` settings for speech-to-speech models such as GPT Realtime and Gemini Live. See [VAD settings](/docs/vad-settings#vad-with-sts-models) and [STT settings](/docs/stt-settings#stt-settings-with-sts-models).

#### Advanced Settings `sounds`

- Added `sounds` settings to enable or disable Assistant thinking sounds. See [Sounds settings](/docs/sounds-settings).</description>
</item>
<item>
<title>1.6.0</title>
<link>https://developers.reecall.com/changelog/160</link>
<guid>https://developers.reecall.com/changelog/160</guid>
<pubDate>Tue, 14 Apr 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Features

#### Advanced settings

- Added [Advanced Settings](/docs/advanced-settings), a reusable configuration resource for:
  - Speech-to-text keyterms and endpointing.
  - Voice activity detection thresholds, silence duration, and interruption control.

#### Startup request

- Assistants can send an HTTP request during call startup to fetch context or trigger an action in your system. See [Startup Request](/docs/startup-request).

### Improvements

#### New STT models

- **Speechmatics** Standard and Enhanced
- **Assembly AI** Universal-3 Pro and Universal-3 Pro Streaming
- **Mistral** Voxtral Mini Transcribe Realtime

#### New LLMs

- **Mistral** Small 4 and Medium 3.5

### Fixes

#### RPC `EndCall`

- Fixed a bug where the Assistant's `end_conversation` tool failed to call the `EndCall` RPC method.

## Data API

### Improvements

#### KnowledgeBase cascade deletion

- Deleting a Knowledge Base also deletes its Knowledge entries.</description>
</item>
<item>
<title>1.5.0</title>
<link>https://developers.reecall.com/changelog/150</link>
<guid>https://developers.reecall.com/changelog/150</guid>
<pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Features

#### Add `send_http_request`

* Added `send_http_request` so an Assistant can call external APIs during a conversation.

#### Add `send_rpc_request`

* Added `send_rpc_request` so an Assistant can send an RPC request to its connected WebRTC client.</description>
</item>
<item>
<title>1.4.1</title>
<link>https://developers.reecall.com/changelog/141</link>
<guid>https://developers.reecall.com/changelog/141</guid>
<pubDate>Thu, 02 Apr 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

#### Better turn handling

* Improved turn handling for STS models to reduce false interruptions in loud environments.
* Added a LiveKit turn handling model to improve interruption detection.

### Fixes

#### `firstMessage` interruption with STS models

* Fixed a bug where callers could interrupt `firstMessage` and tool call messages when using an STS model.</description>
</item>
<item>
<title>1.4.0</title>
<link>https://developers.reecall.com/changelog/140</link>
<guid>https://developers.reecall.com/changelog/140</guid>
<pubDate>Wed, 18 Mar 2026 00:00:00 GMT</pubDate>
<description>## Metrics API

### Features

#### Conversation usage metrics

* Use `/v1/metrics/:metric` to retrieve time-series data for a single metric, grouped by granularity (`hour`, `day`, `week`, `month`, `year`, `all`).
* Use `/v1/metrics/bulkAll` to retrieve multiple metrics aggregated over a time range in one request.
* Filter by `projectId`, `traceId`, and `context`, such as `assistantId`, to scope results to a project, conversation, or Assistant.
* Metrics with a configured price calculation include a `pricing` field with the estimated cost in EUR. Unpriced time-series metrics omit this field.
* Use `padMissing=true` on `/v1/metrics/:metric` to fill gaps in the time series with zero values.
* Added use-case guides for [conversation metrics](/docs/use-case-fetch-conversation-metrics) and [Assistant metrics](/docs/use-case-fetch-metrics-for-a-specific-assistant).

#### Available metrics

* `exchangeCount`: number of conversation exchanges.
* `duration`: total conversation duration in seconds.
* `indivisibleDuration`: billed duration blocks in minutes.
* `usage.stt.audioDuration`: speech-to-text audio duration.
* `usage.tts.characters`: characters sent to text-to-speech.
* `usage.conversational.inputTextTokens`: input tokens consumed by the conversational AI.
* `usage.conversational.outputTextTokens`: output tokens produced by the conversational AI.
* `usage.conversational.cachedTextTokens`: cached tokens reused by the conversational AI.
* `usage.realtime.inputTextTokens`: input text tokens for realtime AI.
* `usage.realtime.outputTextTokens`: output text tokens for realtime AI.
* `usage.realtime.inputAudioTokens`: input audio tokens for realtime AI.
* `usage.realtime.outputAudioTokens`: output audio tokens for realtime AI.
* `usage.realtime.cachedAudioTokens`: cached audio tokens for realtime AI.
* `usage.postProcessing.inputTextTokens`: input tokens for post-processing.
* `usage.postProcessing.outputTextTokens`: output tokens for post-processing.
* `usage.postProcessing.cachedTextTokens`: cached tokens for post-processing.

## Data API

* The `Variable` model is available in Blueprints.</description>
</item>
<item>
<title>1.3.2</title>
<link>https://developers.reecall.com/changelog/132</link>
<guid>https://developers.reecall.com/changelog/132</guid>
<pubDate>Mon, 16 Mar 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

#### User away smart handling

* When a caller is inactive, the Assistant prompts them three times at 5-second intervals before ending the conversation. If the caller responds, the conversation resumes.

### Fixes

#### WebRTC `transfer_conversation` tool inactivity timeout

* Fixed a bug where the Assistant waited indefinitely for the WebRTC client to resolve a transfer request. The Assistant ends the conversation after 5 minutes without a resolution.</description>
</item>
<item>
<title>1.3.1</title>
<link>https://developers.reecall.com/changelog/131</link>
<guid>https://developers.reecall.com/changelog/131</guid>
<pubDate>Wed, 11 Mar 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Fixes

#### Missing final Assistant message

* Fixed a bug where the Assistant's message was missing from `Exchange.messages` if the caller disconnected or hung up mid-sentence.

### Improvements

#### Better interruption detection

* Interruption detection requires at least two detected words and 500 ms of recorded speech.

#### Transfer default message

* The Assistant generates a `preTransferSentence` from the conversation context when a `transfer_conversation` destination has none configured.

## Data API

### Improvements

#### `conversation_ended_by` metadata in Exchange

* Added `conversation_ended_by` to Exchange resources. Its value is `caller` or `assistant`, depending on who ended the conversation.

#### `interrupted` metadata in Exchange messages

* Messages in `Exchange.messages` include `"metadata": { "interrupted": true | false }` to indicate whether speech was interrupted.</description>
</item>
<item>
<title>1.3.0</title>
<link>https://developers.reecall.com/changelog/130</link>
<guid>https://developers.reecall.com/changelog/130</guid>
<pubDate>Fri, 27 Feb 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Features

#### Data injection

* Inject data when a conversation starts. Each key becomes a dynamic variable, resolved with `{key}` in the Assistant's instructions, first message, and other templated fields. See [Data injection](/docs/data-injection).
* Inject data through UUI on [SIP Channels](/docs/data-injection#injecting-data-via-sip-channels).
* Set `injectedData` in the `POST /calls/:channelId` request payload for [WebRTC Channels](/docs/data-injection#injecting-data-via-webrtc-channels).

### Improvements

#### Startup time latency

* Reduced the time between connecting to a conversation and the Assistant being ready by 50%.

#### Set fixed audio output samplerate

* Set audio output to 48 kHz to match the native Opus sample rate and remove a resampling step before WebRTC encoding.

#### Ultravox support

* Added the Ultravox realtime models Gemma3 27B Preview, Llama 3.3 70B, and Ultravox Realtime.
* Added Inworld and ElevenLabs voices for Ultravox.

#### Gradium support

* Added the default Gradium STT model.
* Added the default Gradium TTS model and voices.

#### GPT Realtime 1.5 &amp; Mini support

* Added the `gpt-realtime-1.5` and `gpt-realtime-mini` models.

## Calls API

### Features

#### Data injection

* `POST /calls/:channelId` accepts an `injectedData` object. See [WebRTC data injection](/docs/data-injection#injecting-data-via-webrtc-channels).</description>
</item>
<item>
<title>1.2.1</title>
<link>https://developers.reecall.com/changelog/121</link>
<guid>https://developers.reecall.com/changelog/121</guid>
<pubDate>Fri, 27 Feb 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Improvements

#### Extend External ID support to SIP UUI

* Assistants can extract the external ID from the SIP UUI header.

## Data API

### Improvements

#### New ElevenLabs voice

* Added the voice "Mademoiselle French - For Audiotel".

### Bug fixes

#### Inconsistent LiveKit Trunk deletion

* Fixed a bug where deleting a SIP Channel sometimes left its LiveKit Trunk behind.</description>
</item>
<item>
<title>1.2.0</title>
<link>https://developers.reecall.com/changelog/120</link>
<guid>https://developers.reecall.com/changelog/120</guid>
<pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Features

#### Conversational data extraction

* Configure `dataExtractionSchema` to extract data, such as caller intent, after a conversation ends. The result is stored in the Exchange's `data` property. See [Data extraction](/docs/conversational-data-extraction).

### Bug fixes

#### STS + TTS hybrid mode

* Fixed a bug where Assistants using STS + TTS hybrid mode stayed silent.

#### Abrupt final sentence cut with STS

* Fixed a bug where the final sentence from an STS Assistant was cut off before playback finished.

## Data API

### Features

#### Blueprints

* Provision one or more resources in a single operation using a [Blueprint](/docs/blueprints-overview). Each Blueprint defines the entities to create, with shared field injection through `overrides` and runtime value substitution through `context`.

* Use named entries to reference resources created earlier in the same Blueprint, such as linking an Assistant to a Knowledge Base created in the same run.
* Run a Blueprint inline via `POST /core/blueprints/run`, or store it as a reusable record and invoke it by ID via `POST /core/blueprints/:id/run`.

#### Project level external ID

* Set the optional `externalId` field when creating or updating a Project with `POST /core/projects` or `PATCH /core/projects/:id`. Use it to store the identifier of an entity in your own system.

### Bug fixes

#### Channel validation conflict

* Fixed an API validation regression where SIP validation rules prevented WebRTC Channels from being created or updated.</description>
</item>
<item>
<title>1.1.0</title>
<link>https://developers.reecall.com/changelog/110</link>
<guid>https://developers.reecall.com/changelog/110</guid>
<pubDate>Wed, 04 Feb 2026 00:00:00 GMT</pubDate>
<description>## AI Assistants

### Features

#### Speech-to-speech (STS) support

* Assistants can use STS instead of STT + LLM + TTS to reduce turn latency.

#### Knowledge Base support

* Assistants can use your Knowledge Bases during conversations.

#### External ID support

* Added `externalId` to associate conversations with identifiers from your external systems.
* Added support for the custom SIP header `X-External-ID`.

### Improvements

#### Exchange lifecycle management

* Exchanges are created at conversation start with partial data and an `inProgress` status. At conversation end, they receive the complete conversation data and a `completed` status.

#### Gladia STT endpointing

* Improved Gladia speech-to-text endpointing configuration for more accurate speech detection.

### Bug fixes

#### Variable resolution

* Fixed dynamic variable substitution in Assistant instructions.

#### Final Assistant sentence

* Fixed a bug where the system hung up before the Assistant's final sentence finished playing.

***

## Data API

### Features

&lt;span id="speech-to-speech-sts-support--beta-" /&gt;

#### Speech-to-speech (STS) support (beta)

* Added the STS entity for managing real-time voice interactions.
* Added `/ai/sts` for STS configuration management, initially supporting `gpt-realtime`.

#### Knowledge Base support

* Added `/ai/knowledges` to create knowledge entries.
* Added `/ai/knowledgeBases` to group knowledge entries into Knowledge Bases.

### Improvements

#### Enhanced API query capabilities

* Added the `select` parameter to `getById` operations to choose response fields.

#### External ID support

* Added `externalId` to the Exchange entity to associate it with an external system's identifier.

#### SIP Channels configuration enhancements

* The `/conversational/channels` endpoint accepts `krispEnabled` and `includeSipHeaders`.

#### Exchange root data

* Added conversation fields to the Exchange entity root:
  * `duration`: exchange duration in seconds
  * `assistantId`: ID of the Assistant that participated in the Exchange

***

## Calls API

### Features

#### External ID support

* `POST /calls/:channelId` accepts `externalId` in its request payload.</description>
</item>
</channel>
</rss>
