amanda-vapi · Nov 11, 2026 · Nov 11, 2026
diff --git a/fern/assistants/pronunciation-dictionaries.mdx b/fern/assistants/pronunciation-dictionaries.mdx
@@ -252,7 +252,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
 
 <Steps>
   <Step title="Create an ElevenLabs Pronunciation Dictionary">
-    For Vapi v1 built-in voices, create the pronunciation dictionary through the ElevenLabs endpoint shown above. The response includes both a dictionary ID and a `versionId`; keep both values.
+    For Vapi v1 built-in voices, create the pronunciation dictionary through the ElevenLabs endpoint shown above. The response includes both a dictionary ID and a `versionId`. Keep the dictionary ID, and keep the `versionId` if you want to pin that version.
 
     Vapi built-in voices use a unified `pronunciationDictionary` field, but most v1 built-in voices route through ElevenLabs under the hood. Do not assume a Cartesia dictionary ID works with every Vapi built-in voice. Cartesia dictionary IDs only apply to Vapi voices that are routed to a Cartesia Sonic voice path.
   </Step>
@@ -277,7 +277,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
     ```
 
     <Note>
-      For ElevenLabs-backed dictionaries, `versionId` is required. It pins the exact dictionary version that the Vapi voice should use.
+      For ElevenLabs-backed dictionaries, `versionId` is optional. Set it to pin the exact dictionary version that the Vapi voice should use. To use the dictionary's latest version, leave out `versionId` and set `provider` to `11labs`.
     </Note>
   </Step>
 

diff --git a/fern/calls/assistant-based-warm-transfer.mdx b/fern/calls/assistant-based-warm-transfer.mdx
@@ -195,6 +195,8 @@ Use these fields to control the transfer assistant and the two call legs. See th
 | `transferAssistant.maxDurationSeconds` | Maximum length of the transfer-assistant conversation | 120 seconds; allowed range is 10–43,200 seconds |
 | `transferAssistant.silenceTimeoutSeconds` | Silence allowed before the transfer is canceled | 30 seconds; allowed range is 5–3,600 seconds |
 | `transferAssistant.model` | Model and instructions used for the operator conversation | Required when you configure `transferAssistant` |
+| `transferAssistant.hooks` | Hooks the transfer assistant runs during the operator conversation. The operator counts as the customer, so `customer.speech.timeout` fires on operator silence | `call.ending` and `call.timeElapsed` hooks aren't allowed. A `tool` action needs an inline `tool`, not a `toolId` |
+| `transferAssistant.assistantHooksInheritEnabled` | Whether the transfer assistant also runs the original assistant's hooks during the operator conversation | `true`. When `false`, only `transferAssistant.hooks` and the original assistant's `call.ending` hooks run |
 | `holdAudioUrl` | MP3 or WAV audio played to the customer while on hold | Default hold audio |
 | `transferCompleteAudioUrl` | MP3 or WAV audio played to the destination after the introduction | No custom completion audio |
 | `fallbackPlan` | Customer message and end-call behavior after a failed warm transfer | If omitted, the original assistant says "Could not transfer the call." and continues the conversation |
@@ -255,6 +257,7 @@ Open the affected call in [**Calls**](/observability/logs/call-logs) under **Log
 | The customer hears the wrong audio | Hold audio was configured as a tool message | Put customer hold audio in `transferPlan.holdAudioUrl`. Use `transferCompleteAudioUrl` for audio played to the destination after the introduction. |
 | The customer cannot continue after a failed transfer | `fallbackPlan.endCallEnabled` is `true` | Set it to `false` so the original assistant remains on the call. |
 | The transfer ends during a long operator interaction | A duration or silence timeout is too short | Increase `maxDurationSeconds` or `silenceTimeoutSeconds` within the supported ranges. |
+| The whole call ends when the operator goes quiet | The transfer assistant inherited a `customer.speech.timeout` hook with an `endCall` action from the original assistant | Set `transferAssistant.assistantHooksInheritEnabled` to `false`, and add any hooks the operator conversation needs to `transferAssistant.hooks`. |
 
 ## API reference
 

diff --git a/fern/calls/call-ended-reason.mdx b/fern/calls/call-ended-reason.mdx
@@ -137,7 +137,7 @@ Each voice provider has specific error codes. Common patterns:
 - `*-quota-exceeded` / `*-out-of-credits` — Voice provider credits exhausted.
 - `*-unauthorized-access` / `*-invalid-api-key` — Voice provider credential issue.
 - `*-unsupported-model` — The voice provider rejected the configured model.
-- `*-socket-hang-up` / `*-500-server-error` / `*-503-server-error` — Voice provider infrastructure issue.
+- `*-socket-hang-up` / `*-500-server-error` / `*-502-server-error` / `*-503-server-error` — Voice provider infrastructure issue.
 
 **Supported providers:** ElevenLabs, Cartesia, Deepgram, Azure, OpenAI, Rime AI, Smallest AI, Neuphonic, Hume, Sesame, Inworld, Minimax, WellSaid, Custom Voice.
 
@@ -151,7 +151,14 @@ Common transcriber error patterns:
 - `*-returning-403-*` — Model access denied on the transcriber.
 - `*-returning-500-*` / `*-returning-502-*` — Transcriber provider server error.
 
-**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Custom Transcriber.
+**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Reson8, Custom Transcriber.
+
+Soniox, xAI, and Reson8 report these more specific reasons instead of a generic failure:
+
+- `*-transcriber-auth-failed` — The transcriber provider rejected the credentials.
+- `*-transcriber-invalid-config` — The transcriber provider rejected the transcriber settings.
+- `*-transcriber-rate-limited` — The transcriber provider rate-limited the request.
+- `reson8-transcriber-closed` — The Reson8 connection closed unexpectedly.
 
 ## Transfer errors
 

diff --git a/fern/docs.yml b/fern/docs.yml
@@ -884,6 +884,8 @@ navigation:
                     path: providers/transcriber/google.mdx
                   - page: OpenAI
                     path: providers/transcriber/openai.mdx
+                  - page: Reson8
+                    path: providers/transcriber/reson8.mdx
                   - page: Soniox
                     path: providers/transcriber/soniox.mdx
                   - page: Speechmatics

diff --git a/fern/gpt-live/configuration.mdx b/fern/gpt-live/configuration.mdx
@@ -101,7 +101,7 @@ These fields belong to the assistant object. See [Create Assistant](/api-referen
 | `model.tools` | Inline base tool definitions, available whether or not a skill is loaded |
 | `model.toolIds` | IDs of saved base tools |
 | `voice.provider` | `openai` |
-| `voice.voiceId` | One of the [22 supported voices](#voices) |
+| `voice.voiceId` | One of the [31 supported voices](#voices) |
 
 ## Prompt defaults and overrides
 

diff --git a/fern/gpt-live/overview.mdx b/fern/gpt-live/overview.mdx
@@ -66,7 +66,7 @@ Vapi connects GPT-Live to your phone numbers and tools, and provides call record
 
 - Browser, Twilio, Vapi SIP, and WebSocket calls.
 - Function, API request, and MCP tools, Google Calendar, Google Sheets, and Slack tools, plus built-in Hang Up, transfer, and DTMF tools.
-- Speaker and reasoner prompts, reasoner skills, personality packs, and 22 voices.
+- Speaker and reasoner prompts, reasoner skills, personality packs, and 31 voices.
 - Idle-message hooks and HTTP live call control.
 - Transcripts, recordings, structured outputs, scorecards, Boards, Monitoring, and Voice Simulations.
 

diff --git a/fern/providers/model/anthropic-bedrock.mdx b/fern/providers/model/anthropic-bedrock.mdx
@@ -17,7 +17,15 @@ Vapi's Anthropic Bedrock integration allows you to connect your own AWS Bedrock
 
 For the current Anthropic Claude models available through Amazon Bedrock, see [Anthropic models in the Amazon Bedrock documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-anthropic.html). Model availability varies by AWS Region.
 
-For additional API configuration options, review the [`AnthropicBedrockModel` fields](/api-reference/assistants/create#request.body.model.AnthropicBedrock) in the Create Assistant API reference.
+Some Claude models are available through Bedrock's global cross-Region inference profiles. Their model IDs start with `global.`. A global profile can route requests to supported commercial AWS Regions worldwide.
+
+To use a global profile, grant access to the profile, its foundation model in the source Region, and its global foundation model ARN. See the [`AnthropicBedrockModel` fields](/api-reference/assistants/create#request.body.model.AnthropicBedrock) for the model IDs Vapi accepts.
+
+For more information, see the following Amazon Bedrock documentation:
+
+- [Cross-Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html)
+- [Global cross-Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/global-cross-region-inference.html), including its IAM policy requirements
+- [Supported Regions and models for inference profiles](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html)
 
 ### Prerequisites
 
@@ -46,11 +54,15 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
   <Step title="Attach the Trust Policy">
     Configure the trust policy to allow Vapi's AWS account to assume this role.
 
+    An External ID is optional. If you use one, enter the same unique value in the trust policy and Vapi credential. Both examples trust Vapi's production AWS account.
+
+    For more information about these policies, see AWS's guides to [creating a role with a custom trust policy](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_create_for-custom.html) and [using External IDs for third-party access](https://docs.aws.amazon.com/IAM/latest/UserGuide/id_roles_common-scenarios_third-party.html).
+
     <Tabs>
-      <Tab title="Without External ID">
-        Use this simpler policy if you don't need the additional security of an External ID:
+      <Tab title="With External ID">
+        Replace `YOUR_UNIQUE_EXTERNAL_ID` with a unique value before use. AWS recommends an External ID for third-party cross-account access.
 
-        ```json title="Trust Policy (Basic)"
+        ```json title="Trust policy with External ID"
         {
           "Version": "2012-10-17",
           "Statement": [
@@ -59,16 +71,21 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
               "Principal": {
                 "AWS": "arn:aws:iam::533267069243:root"
               },
-              "Action": "sts:AssumeRole"
+              "Action": "sts:AssumeRole",
+              "Condition": {
+                "StringEquals": {
+                  "sts:ExternalId": "YOUR_UNIQUE_EXTERNAL_ID"
+                }
+              }
             }
           ]
         }
         ```
       </Tab>
-      <Tab title="With External ID">
-        Use this policy if you want the additional security of an External ID:
+      <Tab title="Without External ID">
+        Use this policy only if you do not require an External ID for the role. It does not check which Vapi customer the request is for.
 
-        ```json title="Trust Policy (With External ID)"
+        ```json title="Trust policy without External ID"
         {
           "Version": "2012-10-17",
           "Statement": [
@@ -77,85 +94,61 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
               "Principal": {
                 "AWS": "arn:aws:iam::533267069243:root"
               },
-              "Action": "sts:AssumeRole",
-              "Condition": {
-                "StringEquals": {
-                  "sts:ExternalId": "YOUR_EXTERNAL_ID"
-                }
-              }
+              "Action": "sts:AssumeRole"
             }
           ]
         }
         ```
-
-        Replace `YOUR_EXTERNAL_ID` with your chosen value. You'll use the same value when creating the Vapi credential.
       </Tab>
     </Tabs>
-
-    <Note>
-    **About External ID**: The External ID is an optional security feature that provides an additional layer of protection for cross-account access. If you choose to use one, specify the same value in both your IAM trust policy and the Vapi credential configuration.
-    </Note>
   </Step>
 
   <Step title="Attach the Permissions Policy">
-    Create and attach a permissions policy that grants access to Bedrock model invocation.
+    Use this policy when your Vapi credential Region is `us-east-1`. It allows Claude Haiku 5.5 through the US inference profile, which can route to `us-east-1`, `us-east-2`, or `us-west-2`. Replace `YOUR_AWS_ACCOUNT_ID` with your AWS account ID before creating the policy.
 
-    <Tabs>
-      <Tab title="Broad Access">
-        Use this policy to grant access to all Anthropic models across all regions:
-
-        ```json title="Permissions Policy (All Models)"
+    ```json title="Permissions policy: us-east-1"
+    {
+      "Version": "2012-10-17",
+      "Statement": [
         {
-          "Version": "2012-10-17",
-          "Statement": [
-            {
-              "Effect": "Allow",
-              "Action": [
-                "bedrock:InvokeModel",
-                "bedrock:InvokeModelWithResponseStream"
-              ],
-              "Resource": [
-                "arn:aws:bedrock:*::foundation-model/anthropic.*",
-                "arn:aws:bedrock:*:*:inference-profile/us.anthropic.*"
-              ]
-            }
-          ]
-        }
-        ```
-      </Tab>
-      <Tab title="Restrictive Access">
-        Use this policy to limit access to specific models and regions:
-
-        ```json title="Permissions Policy (Specific Models)"
+          "Effect": "Allow",
+          "Action": [
+            "bedrock:InvokeModel",
+            "bedrock:InvokeModelWithResponseStream"
+          ],
+          "Resource": "arn:aws:bedrock:us-east-1:YOUR_AWS_ACCOUNT_ID:inference-profile/us.anthropic.claude-haiku-5-5"
+        },
         {
-          "Version": "2012-10-17",
-          "Statement": [
-            {
-              "Effect": "Allow",
-              "Action": [
-                "bedrock:InvokeModel",
-                "bedrock:InvokeModelWithResponseStream"
-              ],
-              "Resource": [
-                "arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-5-sonnet-*",
-                "arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-7-sonnet-*",
-                "arn:aws:bedrock:us-east-1:*:inference-profile/us.anthropic.claude-3-5-sonnet-*",
-                "arn:aws:bedrock:us-east-1:*:inference-profile/us.anthropic.claude-3-7-sonnet-*"
-              ]
+          "Effect": "Allow",
+          "Action": [
+            "bedrock:InvokeModel",
+            "bedrock:InvokeModelWithResponseStream"
+          ],
+          "Resource": [
+            "arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-haiku-5-5",
+            "arn:aws:bedrock:us-east-2::foundation-model/anthropic.claude-haiku-5-5",
+            "arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-haiku-5-5"
+          ],
+          "Condition": {
+            "StringEquals": {
+              "bedrock:InferenceProfileArn": "arn:aws:bedrock:us-east-1:YOUR_AWS_ACCOUNT_ID:inference-profile/us.anthropic.claude-haiku-5-5"
             }
-          ]
+          }
         }
-        ```
+      ]
+    }
+    ```
 
-        <Tip>
-        Replace `us-east-1` with your preferred AWS region. You can also add or remove specific model versions based on your needs.
-        </Tip>
-      </Tab>
-    </Tabs>
+    To adapt the policy, check the exact profile ID, supported source Regions, and destination Regions in the [AWS Claude Haiku 5.5 model card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html). You can also call [GetInferenceProfile](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-view.html) from your source Region with an AWS identity that has `bedrock:GetInferenceProfile` permission. Update the profile ARN, foundation model ARNs, and `bedrock:InferenceProfileArn` condition together. Check the [`AnthropicBedrockModel` fields](/api-reference/assistants/create#request.body.model.AnthropicBedrock) for the model IDs Vapi accepts.
+
+    For more information about the required resources, see AWS's [inference profile prerequisites](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-prereq.html). Global profiles require a different policy shape; see AWS's [global cross-Region inference guidance](https://docs.aws.amazon.com/bedrock/latest/userguide/global-cross-region-inference.html).
+
+    Before attaching the policy, use [IAM Access Analyzer policy validation](https://docs.aws.amazon.com/IAM/latest/UserGuide/access-analyzer-policy-validation.html) to review its syntax and permissions. Other policies and service control policies can also affect the role's effective access.
 
     To attach the policy:
+
     1. In the IAM Console, go to **Policies** and click **Create policy**
-    2. Select **JSON** and paste your chosen policy
+    2. Select **JSON** and paste the policy
     3. Name the policy (e.g., `VapiBedrockInvokePolicy`)
     4. Attach the policy to your IAM role
   </Step>
@@ -173,7 +166,7 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
         "authenticationPlan": {
           "type": "aws-sts",
           "roleArn": "arn:aws:iam::YOUR_AWS_ACCOUNT_ID:role/VapiBedrockRole",
-          "externalId": "your-optional-external-id"
+          "externalId": "YOUR_UNIQUE_EXTERNAL_ID"
         }
       }'
     ```
@@ -184,11 +177,9 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
     | `region` | AWS region where Bedrock is enabled (e.g., `us-east-1`) |
     | `authenticationPlan.type` | Must be `aws-sts` for role assumption |
     | `authenticationPlan.roleArn` | The ARN of the IAM role you created |
-    | `authenticationPlan.externalId` | Optional: Your chosen External ID for additional security |
+    | `authenticationPlan.externalId` | Optional; include only with the matching External ID trust policy |
 
-    <Tip>
-    If you don't need an External ID, you can remove the `Condition` block from your trust policy entirely.
-    </Tip>
+    If you choose the trust policy without an External ID, omit the `externalId` field from the request.
   </Step>
 </Steps>
 

diff --git a/fern/providers/transcriber/assembly-ai.mdx b/fern/providers/transcriber/assembly-ai.mdx
@@ -44,6 +44,7 @@ Both Universal Pro models support additional configuration:
 - `agentContextAutoUpdateEnabled`: Automatically send what the assistant just said as agent context after every assistant turn. Defaults to `false`.
 - `languageCodes`: Steer automatic language detection with language codes such as `["en", "es"]`.
 - `keytermsPrompt`: Boost recognition of domain-specific terms. Included at no extra cost on the Universal Pro models.
+- `confidenceThreshold`: Discard caller transcripts with a confidence below this value, from `0` to `1`. Universal Pro models don't filter by confidence unless you set it. In the dashboard, turn on **Low-confidence filter** in the transcriber settings.
 
 ### Automatic agent context
 

diff --git a/fern/providers/transcriber/deepgram.mdx b/fern/providers/transcriber/deepgram.mdx
@@ -112,7 +112,7 @@ The Nova 3 column applies to Nova 3 and Nova 3 General, and the Nova 2 column ap
 | Macedonian | `mk` | X |  |  |  |  |  |
 | Malay | `ms` | X |  | X |  |  |  |
 | Marathi | `mr` | X |  |  |  |  |  |
-| Multilingual | `multi` | X |  | X |  |  |  |
+| Multilingual | `multi` | X | X | X |  |  |  |
 | Norwegian | `no` | X |  | X |  |  |  |
 | Persian | `fa` | X |  |  |  |  |  |
 | Polish | `pl` | X |  | X |  |  |  |
@@ -139,7 +139,7 @@ The Nova 3 column applies to Nova 3 and Nova 3 General, and the Nova 2 column ap
 
 ### Multilingual transcription
 
-For Nova 3 or Nova 2, set `transcriber.language` to `multi`. For Flux, select `flux-general-multi` and omit `transcriber.languages` to use automatic language detection. You can also provide a `languages` array to give Flux language hints for multilingual or code-switching conversations. See [Deepgram's Flux language prompting documentation](https://developers.deepgram.com/docs/flux/language-prompting).
+For Nova 3, Nova 3 Medical, or Nova 2, set `transcriber.language` to `multi`. For Flux, select `flux-general-multi` and omit `transcriber.languages` to use automatic language detection. You can also provide a `languages` array to give Flux language hints for multilingual or code-switching conversations. See [Deepgram's Flux language prompting documentation](https://developers.deepgram.com/docs/flux/language-prompting).
 
 ## Related