Skip to content

Commit a99f434

Browse files
quantstruct-botquantstruct-bot
authored
Add changelog for 2025-08-11 (#609)
1 parent 4f16438 commit a99f434

File tree

5 files changed

+152
-0
lines changed

5 files changed

+152
-0
lines changed

‎fern/changelog/2025-08-01.mdx‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,35 @@
1+
# New Features & Enhancements
2+
3+
1. **Enhanced Call [`Artifacts`](https://api.vapi.ai/api#:~:text=Artifact)**: You can now store detailed information about call workflows and outcomes using [`Artifact`](https://api.vapi.ai/api#:~:text=Artifact) objects. Key properties include:
4+
- `nodes`: History of workflow nodes executed during the call.
5+
- `messages`: All messages spoken during the call.
6+
- `logUrl`: **New!** Direct URL to detailed call logs for debugging.
7+
- `pcapUrl`: Packet capture URL for phone calls (provider: `vapi` or `byo-phone-number`).
8+
- `recording`: Recording URL (requires `assistant.artifactPlan.recordingEnabled`).
9+
- `transcript`: Convenient full call transcript.
10+
- `variableValues`: Final workflow variable states.
11+
- `messagesOpenAIFormatted`: Spoken messages, formatted for OpenAI.
12+
13+
<Warning>
14+
`recordingUrl`, `videoRecordingUrl`, `stereoRecordingUrl`, and `videoRecordingStartDelaySeconds` are now deprecated in favor of the new `recording` and related properties within the `Artifact` object.
15+
</Warning>
16+
17+
2. **Improved Azure Speech Segmentation Tuning**: You can now fine-tune speech segmentation in your [`Azure Speech Transcriber`](https://api.vapi.ai/api#:~:text=AzureSpeechTranscriber) using `segmentationStrategy`, `segmentationMaximumTimeMs`, and `segmentationSilenceTimeoutMs` properties for better transcription control. This applies to both [`Azure Speech Transcriber`](https://api.vapi.ai/api#:~:text=AzureSpeechTranscriber) and [`Fallback Azure Speech Transcriber`](https://api.vapi.ai/api#:~:text=FallbackAzureSpeechTranscriber).
18+
19+
<Warning>
20+
The `segmentationMaxTimeMs` property in [`AzureSpeechTranscriber`](https://api.vapi.ai/api#:~:text=AzureSpeechTranscriber) has been replaced by `segmentationMaximumTimeMs` for consistency.
21+
</Warning>
22+
23+
## Deprecations
24+
<CardGroup cols={3}>
25+
<Card title="Assistant & Related Objects" icon="cog">
26+
<code>messagePlan</code> and <code>backgroundDenoisingEnabled</code> are now part of <code>Assistant.backgroundSpeechDenoisingPlan</code> instead of <code>Assistant</code> and <code>AssistantOverrides</code> directly.
27+
</Card>
28+
<Card title="Org" icon="building">
29+
<code>stripeCustomerId</code> is now part of <code>Subscription</code> instead of <code>Org</code>.
30+
</Card>
31+
<Card title="AzureSpeechTranscriber" icon="brands microsoft">
32+
<code>segmentationMaxTimeMs</code> property has been renamed to <code>segmentationMaximumTimeMs</code> for consistency.
33+
</Card>
34+
</CardGroup>
35+

‎fern/changelog/2025-08-02.mdx‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
# Azure Speech Segmentation Strategy Tuning
2+
3+
1. You can now tune `Assistant.transcriber[provider="AzureSpeechTranscriber"].segmentationStrategy` using `"Default"`, `"Time"`, and `"Semantic"` strategies, offering more control over phrase boundary detection.

‎fern/changelog/2025-08-03.mdx‎

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
2+
#### 🎤 New Gladia Transcription Provider Support
3+
1. **Custom vocabulary support**: Enable a custom vocabulary with [`Gladia`](https://api.vapi.ai/api#:~:text=GladiaTranscriber) using `Assistant.transcriber[provider="GladiaTranscriber"].customVocabularyEnabled`. You can also specify simple strings or detailed objects with fields for value, language, intensity, and alternative pronunciations using `Assistant.transcriber[provider="GladiaTranscriber"].customVocabularyConfig` - letting you fine-tune recognition of domain-specific terms.
4+
5+
2. **Endpointing & Speech Threshold**: Configure endpointing time (wait time before considering speech ended) and speech sensitivity, enabling more accurate and responsive transcription with `Assistant.transcriber[provider="GladiaTranscriber"].endpointing` and `Assistant.transcriber[provider="GladiaTranscriber"].speechThreshold`.
6+
7+
3. **Prosody & Audio Enhancer**: Optionally enable prosody (for transcribing non-verbal cues like laughter) and audio enhancement for improved accuracy with `Assistant.transcriber[provider="GladiaTranscriber"].prosodyEnabled` and `Assistant.transcriber[provider="GladiaTranscriber"].audioEnhancerEnabled`.
8+
9+
4. **Flexible Language Detection**: Choose between manual and automatic language detection modes with `Assistant.transcriber[provider="GladiaTranscriber"].languageDetectionMode`.
10+
11+
5. **Confidence Thresholds & Hints**: Discard low-confidence transcripts and provide context hints for improved accuracy with `Assistant.transcriber[provider="GladiaTranscriber"].confidenceThreshold` and `Assistant.transcriber[provider="GladiaTranscriber"].hints`.
12+
13+
## 💳 Subscription Updates
14+
15+
<CardGroup cols={3}>
16+
<Card title="RBAC" icon="user-shield">
17+
<b>Role-based access control (RBAC):</b><br />
18+
Enable RBAC for your subscription using <code>Subscription.rbacEnabled</code>.
19+
</Card>
20+
<Card title="Call & Chat Retention" icon="clock-rotate-left">
21+
<b>Retention settings:</b><br />
22+
Configure how long calls and chats are stored with <code>Subscription.callRetentionDays</code> and <code>Subscription.chatRetentionDays</code>.
23+
</Card>
24+
<Card title="Minutes Included Reset Frequency" icon="rotate">
25+
<b>Reset frequency:</b><br />
26+
Set how often included minutes reset using <code>Subscription.minutesIncludedResetFrequency</code>.
27+
</Card>
28+
</CardGroup>

‎fern/changelog/2025-08-08.mdx‎

Lines changed: 29 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
1+
# New: Smarter Conditions & Security Filters
2+
3+
1. **New Condition & Filter Types**: You can now use the following new condition and filter types to build more robust rejection plans and security filter plans:
4+
- **MessageTarget**: Target specific messages by role and position for conditions using `Assistant.hooks.do[type=tool].tool.rejectionPlan.conditions[type=regex].target`.
5+
- **GroupCondition**: Combine multiple conditions using AND/OR logic, with support for recursive nesting using `Assistant.hooks.do[type=tool].tool.rejectionPlan.conditions[type=group]`.
6+
- **RegexCondition**: Flexible pattern matching, with full support for JavaScript regex and negation using `Assistant.hooks.do[type=tool].tool.rejectionPlan.conditions[type=regex]`.
7+
- **LiquidCondition**: Use Liquid templates for complex, context-aware logic using `Assistant.hooks.do[type=tool].tool.rejectionPlan.conditions[type=liquid]`.
8+
- **Security Filters**: New filter types for RCE, XSS, SSRF, SQL injection, prompt injection, and regex-based filtering using `Assistant.compliancePlan.securityFilterPlan.filters`.
9+
10+
2. **Tool Rejection Plans**: You can now use [`Assistant.hooks.do[type=tool].tool.rejectionPlan`](https://api.vapi.ai/api#:~:text=ToolRejectionPlan) in all tool calls to prevent accidental tool execution, enforce confirmation steps, and build more robust conversation flows. This helps you to define complex logic for when a tool call should be rejected, enhancing both safety and call experience. Rejection plans can be built using regex conditions, [Liquid templates](https://liquidjs.com/), or logical groups (AND/OR). For example, you can prevent an `endCall` tool from executing unless the user says goodbye, or block a transfer if the user is actually asking a question.
11+
12+
**Example:**
13+
```json
14+
{
15+
"conditions": [
16+
{
17+
"type": "regex",
18+
"regex": "(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b",
19+
"target": { "position": -1, "role": "user" },
20+
"negate": true
21+
}
22+
]
23+
}
24+
```
25+
26+
3. **Security Filter Plans for Transcripts and Messages**: You can now use [`Assistant.compliancePlan.securityFilterPlan`](https://api.vapi.ai/api#:~:text=SecurityFilterPlan) to define how transcripts and messages are filtered against threats like SQL injection, XSS, prompt injection, and more. Choose between `sanitize`, `reject`, or `replace` when threats are detected, and specify custom replacement text. User messages and transcript objects now include:
27+
- `isFiltered`: Indicates if content was filtered for security.
28+
- `detectedThreats`: Lists detected threats.
29+
- `originalMessage` / `originalTranscript`: Preserves original content if filtering occurred.

‎fern/changelog/2025-08-09.mdx‎

Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
## New: Call Metrics & Artifact Improvements
2+
3+
You can now access detailed call performance metrics and structured output IDs directly from your call artifacts.
4+
5+
<CardGroup cols={3}>
6+
<Card title="Turn Latencies" icon="stopwatch">
7+
<b>Each conversation turn's latency</b>
8+
<br/>
9+
<code>Call.artifact.performanceMetrics.turnLatencies</code>
10+
</Card>
11+
<Card title="Model Latency (avg)" icon="robot">
12+
<b>Average time for the model to generate a response</b>
13+
<br/>
14+
<code>Call.artifact.performanceMetrics.modelLatencyAverage</code>
15+
</Card>
16+
<Card title="Voice Latency (avg)" icon="volume-up">
17+
<b>Average time to synthesize voice</b>
18+
<br/>
19+
<code>Call.artifact.performanceMetrics.voiceLatencyAverage</code>
20+
</Card>
21+
</CardGroup>
22+
23+
<CardGroup cols={3}>
24+
<Card title="Transcriber Latency (avg)" icon="wave-square">
25+
<b>Average time to transcribe voice</b>
26+
<br/>
27+
<code>Call.artifact.performanceMetrics.transcriberLatencyAverage</code>
28+
</Card>
29+
<Card title="Endpointing Latency (avg)" icon="flag-checkered">
30+
<b>Time to detect end of a conversation turn</b>
31+
<br/>
32+
<code>Call.artifact.performanceMetrics.endpointingLatencyAverage</code>
33+
</Card>
34+
<Card title="Turn Latency (avg)" icon="clock">
35+
<b>Average latency to complete a conversation turn</b>
36+
<br/>
37+
<code>Call.artifact.performanceMetrics.turnLatencyAverage</code>
38+
</Card>
39+
</CardGroup>
40+
41+
<Card title="Structured Output IDs & Results" icon="list-ol" size="large">
42+
<b>Track and extract structured outputs from your calls</b>
43+
<ul>
44+
<li>
45+
<b>During call:</b> Access array of output IDs<br/>
46+
<code>Call.artifactPlan.structuredOutputIds</code>
47+
</li>
48+
<li>
49+
<b>After call:</b> Extracted outputs are stored here<br/>
50+
<code>Call.artifact.structuredOutputs</code>
51+
</li>
52+
</ul>
53+
</Card>
54+
55+
<Info>
56+
These improvements help you monitor, debug, and analyze your calls with greater detail.
57+
</Info>

0 commit comments

Comments
 (0)