You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 424b609
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: fern/assistants/pronunciation-dictionaries.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -252,7 +252,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
252
252
253
253
<Steps>
254
254
<Steptitle="Create an ElevenLabs Pronunciation Dictionary">
255
-
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.
255
+
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.
256
256
257
257
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.
258
258
</Step>
@@ -277,7 +277,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
277
277
```
278
278
279
279
<Note>
280
-
For ElevenLabs-backed dictionaries, `versionId` is required. It pins the exact dictionary version that the Vapi voice should use.
280
+
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`.
Copy file name to clipboardExpand all lines: fern/calls/assistant-based-warm-transfer.mdx
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -195,6 +195,8 @@ Use these fields to control the transfer assistant and the two call legs. See th
195
195
|`transferAssistant.maxDurationSeconds`| Maximum length of the transfer-assistant conversation | 120 seconds; allowed range is 10–43,200 seconds |
196
196
|`transferAssistant.silenceTimeoutSeconds`| Silence allowed before the transfer is canceled | 30 seconds; allowed range is 5–3,600 seconds |
197
197
|`transferAssistant.model`| Model and instructions used for the operator conversation | Required when you configure `transferAssistant`|
198
+
|`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`|
199
+
|`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 |
198
200
|`holdAudioUrl`| MP3 or WAV audio played to the customer while on hold | Default hold audio |
199
201
|`transferCompleteAudioUrl`| MP3 or WAV audio played to the destination after the introduction | No custom completion audio |
200
202
|`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
255
257
| 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. |
256
258
| The customer cannot continue after a failed transfer |`fallbackPlan.endCallEnabled` is `true`| Set it to `false` so the original assistant remains on the call. |
257
259
| The transfer ends during a long operator interaction | A duration or silence timeout is too short | Increase `maxDurationSeconds` or `silenceTimeoutSeconds` within the supported ranges. |
260
+
| 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`. |
Copy file name to clipboardExpand all lines: fern/providers/model/anthropic-bedrock.mdx
+65-74Lines changed: 65 additions & 74 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -17,7 +17,15 @@ Vapi's Anthropic Bedrock integration allows you to connect your own AWS Bedrock
17
17
18
18
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.
19
19
20
-
For additional API configuration options, review the [`AnthropicBedrockModel` fields](/api-reference/assistants/create#request.body.model.AnthropicBedrock) in the Create Assistant API reference.
20
+
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.
21
+
22
+
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.
23
+
24
+
For more information, see the following Amazon Bedrock documentation:
-[Global cross-Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/global-cross-region-inference.html), including its IAM policy requirements
28
+
-[Supported Regions and models for inference profiles](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html)
21
29
22
30
### Prerequisites
23
31
@@ -46,11 +54,15 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
46
54
<Steptitle="Attach the Trust Policy">
47
55
Configure the trust policy to allow Vapi's AWS account to assume this role.
48
56
57
+
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.
58
+
59
+
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).
60
+
49
61
<Tabs>
50
-
<Tabtitle="Without External ID">
51
-
Use this simpler policy if you don't need the additional security of an External ID:
62
+
<Tabtitle="With External ID">
63
+
Replace `YOUR_UNIQUE_EXTERNAL_ID` with a unique value before use. AWS recommends an External ID for third-party cross-account access.
52
64
53
-
```json title="Trust Policy (Basic)"
65
+
```json title="Trust policy with External ID"
54
66
{
55
67
"Version": "2012-10-17",
56
68
"Statement": [
@@ -59,16 +71,21 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
59
71
"Principal": {
60
72
"AWS": "arn:aws:iam::533267069243:root"
61
73
},
62
-
"Action": "sts:AssumeRole"
74
+
"Action": "sts:AssumeRole",
75
+
"Condition": {
76
+
"StringEquals": {
77
+
"sts:ExternalId": "YOUR_UNIQUE_EXTERNAL_ID"
78
+
}
79
+
}
63
80
}
64
81
]
65
82
}
66
83
```
67
84
</Tab>
68
-
<Tabtitle="With External ID">
69
-
Use this policy if you want the additional security of an External ID:
85
+
<Tabtitle="Without External ID">
86
+
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.
70
87
71
-
```json title="Trust Policy (With External ID)"
88
+
```json title="Trust policy without External ID"
72
89
{
73
90
"Version": "2012-10-17",
74
91
"Statement": [
@@ -77,85 +94,61 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
77
94
"Principal": {
78
95
"AWS": "arn:aws:iam::533267069243:root"
79
96
},
80
-
"Action": "sts:AssumeRole",
81
-
"Condition": {
82
-
"StringEquals": {
83
-
"sts:ExternalId": "YOUR_EXTERNAL_ID"
84
-
}
85
-
}
97
+
"Action": "sts:AssumeRole"
86
98
}
87
99
]
88
100
}
89
101
```
90
-
91
-
Replace `YOUR_EXTERNAL_ID` with your chosen value. You'll use the same value when creating the Vapi credential.
92
102
</Tab>
93
103
</Tabs>
94
-
95
-
<Note>
96
-
**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.
97
-
</Note>
98
104
</Step>
99
105
100
106
<Steptitle="Attach the Permissions Policy">
101
-
Create and attach a permissions policy that grants access to Bedrock model invocation.
107
+
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.
102
108
103
-
<Tabs>
104
-
<Tabtitle="Broad Access">
105
-
Use this policy to grant access to all Anthropic models across all regions:
Replace `us-east-1` with your preferred AWS region. You can also add or remove specific model versions based on your needs.
152
-
</Tip>
153
-
</Tab>
154
-
</Tabs>
142
+
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.
143
+
144
+
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).
145
+
146
+
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.
155
147
156
148
To attach the policy:
149
+
157
150
1. In the IAM Console, go to **Policies** and click **Create policy**
158
-
2. Select **JSON** and paste your chosen policy
151
+
2. Select **JSON** and paste the policy
159
152
3. Name the policy (e.g., `VapiBedrockInvokePolicy`)
160
153
4. Attach the policy to your IAM role
161
154
</Step>
@@ -173,7 +166,7 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
Copy file name to clipboardExpand all lines: fern/providers/transcriber/assembly-ai.mdx
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -44,6 +44,7 @@ Both Universal Pro models support additional configuration:
44
44
-`agentContextAutoUpdateEnabled`: Automatically send what the assistant just said as agent context after every assistant turn. Defaults to `false`.
45
45
-`languageCodes`: Steer automatic language detection with language codes such as `["en", "es"]`.
46
46
-`keytermsPrompt`: Boost recognition of domain-specific terms. Included at no extra cost on the Universal Pro models.
47
+
-`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.
Copy file name to clipboardExpand all lines: fern/providers/transcriber/deepgram.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -112,7 +112,7 @@ The Nova 3 column applies to Nova 3 and Nova 3 General, and the Nova 2 column ap
112
112
| Macedonian |`mk`| X ||||||
113
113
| Malay |`ms`| X || X ||||
114
114
| Marathi |`mr`| X ||||||
115
-
| Multilingual |`multi`| X || X ||||
115
+
| Multilingual |`multi`| X |X| X ||||
116
116
| Norwegian |`no`| X || X ||||
117
117
| Persian |`fa`| X ||||||
118
118
| 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
139
139
140
140
### Multilingual transcription
141
141
142
-
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).
142
+
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).
0 commit comments