Skip to content

Commit 424b609

Browse files
Doc updates for the What New entries (#1419)
1 parent 9143636 commit 424b609

13 files changed

Lines changed: 193 additions & 90 deletions

‎fern/assistants/pronunciation-dictionaries.mdx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -252,7 +252,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
252252

253253
<Steps>
254254
<Step title="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.
256256

257257
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.
258258
</Step>
@@ -277,7 +277,7 @@ Cartesia pronunciation dictionaries use a `text` and `alias` format. Each entry
277277
```
278278

279279
<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`.
281281
</Note>
282282
</Step>
283283

‎fern/calls/assistant-based-warm-transfer.mdx‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -195,6 +195,8 @@ Use these fields to control the transfer assistant and the two call legs. See th
195195
| `transferAssistant.maxDurationSeconds` | Maximum length of the transfer-assistant conversation | 120 seconds; allowed range is 10–43,200 seconds |
196196
| `transferAssistant.silenceTimeoutSeconds` | Silence allowed before the transfer is canceled | 30 seconds; allowed range is 5–3,600 seconds |
197197
| `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 |
198200
| `holdAudioUrl` | MP3 or WAV audio played to the customer while on hold | Default hold audio |
199201
| `transferCompleteAudioUrl` | MP3 or WAV audio played to the destination after the introduction | No custom completion audio |
200202
| `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
255257
| 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. |
256258
| The customer cannot continue after a failed transfer | `fallbackPlan.endCallEnabled` is `true` | Set it to `false` so the original assistant remains on the call. |
257259
| 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`. |
258261

259262
## API reference
260263

‎fern/calls/call-ended-reason.mdx‎

Lines changed: 9 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -138,7 +138,7 @@ Each voice provider has specific error codes. Common patterns:
138138
- `*-quota-exceeded` / `*-out-of-credits` — Voice provider credits exhausted.
139139
- `*-unauthorized-access` / `*-invalid-api-key` — Voice provider credential issue.
140140
- `*-unsupported-model` — The voice provider rejected the configured model.
141-
- `*-socket-hang-up` / `*-500-server-error` / `*-503-server-error` — Voice provider infrastructure issue.
141+
- `*-socket-hang-up` / `*-500-server-error` / `*-502-server-error` / `*-503-server-error` — Voice provider infrastructure issue.
142142

143143
**Supported providers:** ElevenLabs, Cartesia, Deepgram, Azure, OpenAI, Rime AI, Smallest AI, Neuphonic, Hume, Sesame, Inworld, Minimax, WellSaid, Custom Voice.
144144

@@ -152,7 +152,14 @@ Common transcriber error patterns:
152152
- `*-returning-403-*` — Model access denied on the transcriber.
153153
- `*-returning-500-*` / `*-returning-502-*` — Transcriber provider server error.
154154

155-
**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Custom Transcriber.
155+
**Supported providers:** Deepgram, AssemblyAI, Gladia, Speechmatics, Azure Speech, Google, OpenAI, Soniox, ElevenLabs, Reson8, Custom Transcriber.
156+
157+
Soniox, xAI, and Reson8 report these more specific reasons instead of a generic failure:
158+
159+
- `*-transcriber-auth-failed` — The transcriber provider rejected the credentials.
160+
- `*-transcriber-invalid-config` — The transcriber provider rejected the transcriber settings.
161+
- `*-transcriber-rate-limited` — The transcriber provider rate-limited the request.
162+
- `reson8-transcriber-closed` — The Reson8 connection closed unexpectedly.
156163

157164
## Transfer errors
158165

‎fern/docs.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -892,6 +892,8 @@ navigation:
892892
path: providers/transcriber/google.mdx
893893
- page: OpenAI
894894
path: providers/transcriber/openai.mdx
895+
- page: Reson8
896+
path: providers/transcriber/reson8.mdx
895897
- page: Soniox
896898
path: providers/transcriber/soniox.mdx
897899
- page: Speechmatics

‎fern/gpt-live/configuration.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -101,7 +101,7 @@ These fields belong to the assistant object. See [Create Assistant](/api-referen
101101
| `model.tools` | Inline base tool definitions, available whether or not a skill is loaded |
102102
| `model.toolIds` | IDs of saved base tools |
103103
| `voice.provider` | `openai` |
104-
| `voice.voiceId` | One of the [22 supported voices](#voices) |
104+
| `voice.voiceId` | One of the [31 supported voices](#voices) |
105105

106106
## Prompt defaults and overrides
107107

‎fern/gpt-live/overview.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ Vapi connects GPT-Live to your phone numbers and tools, and provides call record
6666

6767
- Browser, Twilio, Vapi SIP, and WebSocket calls.
6868
- Function, API request, and MCP tools, Google Calendar, Google Sheets, and Slack tools, plus built-in Hang Up, transfer, and DTMF tools.
69-
- Speaker and reasoner prompts, reasoner skills, personality packs, and 22 voices.
69+
- Speaker and reasoner prompts, reasoner skills, personality packs, and 31 voices.
7070
- Idle-message hooks and HTTP live call control.
7171
- Transcripts, recordings, structured outputs, scorecards, Boards, Monitoring, and Voice Simulations.
7272

‎fern/providers/model/anthropic-bedrock.mdx‎

Lines changed: 65 additions & 74 deletions
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,15 @@ Vapi's Anthropic Bedrock integration allows you to connect your own AWS Bedrock
1717

1818
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.
1919

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:
25+
26+
- [Cross-Region inference](https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html)
27+
- [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)
2129

2230
### Prerequisites
2331

@@ -46,11 +54,15 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
4654
<Step title="Attach the Trust Policy">
4755
Configure the trust policy to allow Vapi's AWS account to assume this role.
4856

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+
4961
<Tabs>
50-
<Tab title="Without External ID">
51-
Use this simpler policy if you don't need the additional security of an External ID:
62+
<Tab title="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.
5264

53-
```json title="Trust Policy (Basic)"
65+
```json title="Trust policy with External ID"
5466
{
5567
"Version": "2012-10-17",
5668
"Statement": [
@@ -59,16 +71,21 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
5971
"Principal": {
6072
"AWS": "arn:aws:iam::533267069243:root"
6173
},
62-
"Action": "sts:AssumeRole"
74+
"Action": "sts:AssumeRole",
75+
"Condition": {
76+
"StringEquals": {
77+
"sts:ExternalId": "YOUR_UNIQUE_EXTERNAL_ID"
78+
}
79+
}
6380
}
6481
]
6582
}
6683
```
6784
</Tab>
68-
<Tab title="With External ID">
69-
Use this policy if you want the additional security of an External ID:
85+
<Tab title="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.
7087

71-
```json title="Trust Policy (With External ID)"
88+
```json title="Trust policy without External ID"
7289
{
7390
"Version": "2012-10-17",
7491
"Statement": [
@@ -77,85 +94,61 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
7794
"Principal": {
7895
"AWS": "arn:aws:iam::533267069243:root"
7996
},
80-
"Action": "sts:AssumeRole",
81-
"Condition": {
82-
"StringEquals": {
83-
"sts:ExternalId": "YOUR_EXTERNAL_ID"
84-
}
85-
}
97+
"Action": "sts:AssumeRole"
8698
}
8799
]
88100
}
89101
```
90-
91-
Replace `YOUR_EXTERNAL_ID` with your chosen value. You'll use the same value when creating the Vapi credential.
92102
</Tab>
93103
</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>
98104
</Step>
99105

100106
<Step title="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.
102108

103-
<Tabs>
104-
<Tab title="Broad Access">
105-
Use this policy to grant access to all Anthropic models across all regions:
106-
107-
```json title="Permissions Policy (All Models)"
109+
```json title="Permissions policy: us-east-1"
110+
{
111+
"Version": "2012-10-17",
112+
"Statement": [
108113
{
109-
"Version": "2012-10-17",
110-
"Statement": [
111-
{
112-
"Effect": "Allow",
113-
"Action": [
114-
"bedrock:InvokeModel",
115-
"bedrock:InvokeModelWithResponseStream"
116-
],
117-
"Resource": [
118-
"arn:aws:bedrock:*::foundation-model/anthropic.*",
119-
"arn:aws:bedrock:*:*:inference-profile/us.anthropic.*"
120-
]
121-
}
122-
]
123-
}
124-
```
125-
</Tab>
126-
<Tab title="Restrictive Access">
127-
Use this policy to limit access to specific models and regions:
128-
129-
```json title="Permissions Policy (Specific Models)"
114+
"Effect": "Allow",
115+
"Action": [
116+
"bedrock:InvokeModel",
117+
"bedrock:InvokeModelWithResponseStream"
118+
],
119+
"Resource": "arn:aws:bedrock:us-east-1:YOUR_AWS_ACCOUNT_ID:inference-profile/us.anthropic.claude-haiku-5-5"
120+
},
130121
{
131-
"Version": "2012-10-17",
132-
"Statement": [
133-
{
134-
"Effect": "Allow",
135-
"Action": [
136-
"bedrock:InvokeModel",
137-
"bedrock:InvokeModelWithResponseStream"
138-
],
139-
"Resource": [
140-
"arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-5-sonnet-*",
141-
"arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-3-7-sonnet-*",
142-
"arn:aws:bedrock:us-east-1:*:inference-profile/us.anthropic.claude-3-5-sonnet-*",
143-
"arn:aws:bedrock:us-east-1:*:inference-profile/us.anthropic.claude-3-7-sonnet-*"
144-
]
122+
"Effect": "Allow",
123+
"Action": [
124+
"bedrock:InvokeModel",
125+
"bedrock:InvokeModelWithResponseStream"
126+
],
127+
"Resource": [
128+
"arn:aws:bedrock:us-east-1::foundation-model/anthropic.claude-haiku-5-5",
129+
"arn:aws:bedrock:us-east-2::foundation-model/anthropic.claude-haiku-5-5",
130+
"arn:aws:bedrock:us-west-2::foundation-model/anthropic.claude-haiku-5-5"
131+
],
132+
"Condition": {
133+
"StringEquals": {
134+
"bedrock:InferenceProfileArn": "arn:aws:bedrock:us-east-1:YOUR_AWS_ACCOUNT_ID:inference-profile/us.anthropic.claude-haiku-5-5"
145135
}
146-
]
136+
}
147137
}
148-
```
138+
]
139+
}
140+
```
149141

150-
<Tip>
151-
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.
155147

156148
To attach the policy:
149+
157150
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
159152
3. Name the policy (e.g., `VapiBedrockInvokePolicy`)
160153
4. Attach the policy to your IAM role
161154
</Step>
@@ -173,7 +166,7 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
173166
"authenticationPlan": {
174167
"type": "aws-sts",
175168
"roleArn": "arn:aws:iam::YOUR_AWS_ACCOUNT_ID:role/VapiBedrockRole",
176-
"externalId": "your-optional-external-id"
169+
"externalId": "YOUR_UNIQUE_EXTERNAL_ID"
177170
}
178171
}'
179172
```
@@ -184,11 +177,9 @@ Before configuring Anthropic Bedrock with Vapi, ensure you have:
184177
| `region` | AWS region where Bedrock is enabled (e.g., `us-east-1`) |
185178
| `authenticationPlan.type` | Must be `aws-sts` for role assumption |
186179
| `authenticationPlan.roleArn` | The ARN of the IAM role you created |
187-
| `authenticationPlan.externalId` | Optional: Your chosen External ID for additional security |
180+
| `authenticationPlan.externalId` | Optional; include only with the matching External ID trust policy |
188181

189-
<Tip>
190-
If you don't need an External ID, you can remove the `Condition` block from your trust policy entirely.
191-
</Tip>
182+
If you choose the trust policy without an External ID, omit the `externalId` field from the request.
192183
</Step>
193184
</Steps>
194185

‎fern/providers/transcriber/assembly-ai.mdx‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,7 @@ Both Universal Pro models support additional configuration:
4444
- `agentContextAutoUpdateEnabled`: Automatically send what the assistant just said as agent context after every assistant turn. Defaults to `false`.
4545
- `languageCodes`: Steer automatic language detection with language codes such as `["en", "es"]`.
4646
- `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.
4748

4849
### Automatic agent context
4950

‎fern/providers/transcriber/deepgram.mdx‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -112,7 +112,7 @@ The Nova 3 column applies to Nova 3 and Nova 3 General, and the Nova 2 column ap
112112
| Macedonian | `mk` | X | | | | | |
113113
| Malay | `ms` | X | | X | | | |
114114
| Marathi | `mr` | X | | | | | |
115-
| Multilingual | `multi` | X | | X | | | |
115+
| Multilingual | `multi` | X | X | X | | | |
116116
| Norwegian | `no` | X | | X | | | |
117117
| Persian | `fa` | X | | | | | |
118118
| 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
139139

140140
### Multilingual transcription
141141

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).
143143

144144
## Related
145145

0 commit comments

Comments
 (0)