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
* These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool].
38
38
* This uses Twilio's built-in detection while the VoicemailTool relies on the model to detect if a voicemail was reached.
39
39
* You can use neither of them, one of them, or both of them. By default, Twilio built-in detection is enabled while VoicemailTool is not.
/** These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started. You can check the shape of the messages in ClientMessage schema. */
/** These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,handoff-destination-request,user-interrupted. You can check the shape of the messages in ServerMessage schema. */
/** These are dynamic credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. */
* These are the options for the assistant's transcriber.
164
-
*/
165
-
exporttypeTranscriber=
166
-
|Vapi.AssemblyAiTranscriber
167
-
|Vapi.AzureSpeechTranscriber
168
-
|Vapi.CustomTranscriber
169
-
|Vapi.DeepgramTranscriber
170
-
|Vapi.ElevenLabsTranscriber
171
-
|Vapi.GladiaTranscriber
172
-
|Vapi.GoogleTranscriber
173
-
|Vapi.SpeechmaticsTranscriber
174
-
|Vapi.TalkscriberTranscriber
175
-
|Vapi.OpenAiTranscriber
176
-
|Vapi.CartesiaTranscriber;
177
-
/**
178
-
* These are the options for the assistant's LLM.
179
-
*/
180
-
exporttypeModel=
181
-
|Vapi.AnthropicModel
182
-
|Vapi.AnyscaleModel
183
-
|Vapi.CerebrasModel
184
-
|Vapi.CustomLlmModel
185
-
|Vapi.DeepInfraModel
186
-
|Vapi.DeepSeekModel
187
-
|Vapi.GoogleModel
188
-
|Vapi.GroqModel
189
-
|Vapi.InflectionAiModel
190
-
|Vapi.OpenAiModel
191
-
|Vapi.OpenRouterModel
192
-
|Vapi.PerplexityAiModel
193
-
|Vapi.TogetherAiModel
194
-
|Vapi.XaiModel;
195
-
/**
196
-
* These are the options for the assistant's voice.
197
-
*/
198
-
exporttypeVoice=
199
-
|Vapi.AzureVoice
200
-
|Vapi.CartesiaVoice
201
-
|Vapi.CustomVoice
202
-
|Vapi.DeepgramVoice
203
-
|Vapi.ElevenLabsVoice
204
-
|Vapi.HumeVoice
205
-
|Vapi.LmntVoice
206
-
|Vapi.NeuphonicVoice
207
-
|Vapi.OpenAiVoice
208
-
|Vapi.PlayHtVoice
209
-
|Vapi.RimeAiVoice
210
-
|Vapi.SmallestAiVoice
211
-
|Vapi.TavusVoice
212
-
|Vapi.VapiVoice
213
-
|Vapi.SesameVoice
214
-
|Vapi.InworldVoice
215
-
|Vapi.MinimaxVoice;
216
-
/**
217
-
* This is the mode for the first message. Default is 'assistant-speaks-first'.
218
-
*
219
-
* Use:
220
-
* - 'assistant-speaks-first' to have the assistant speak first.
221
-
* - 'assistant-waits-for-user' to have the assistant wait for the user to speak first.
222
-
* - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points).
* These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool].
237
-
* This uses Twilio's built-in detection while the VoicemailTool relies on the model to detect if a voicemail was reached.
238
-
* You can use neither of them, one of them, or both of them. By default, Twilio built-in detection is enabled while VoicemailTool is not.
0 commit comments