32
32
inflections and tones to the text based on the user's expressions and
33
33
the context of the conversation. The synthesized audio is streamed
34
34
back to the user as an [Assistant
35
- Message](/reference/empathic-voice-interface -evi/chat/chat #receive.AssistantMessage.type ).
35
+ Message](/reference/speech-to-speech -evi/chat#receive.AssistantMessage).
36
36
source :
37
37
openapi : evi-asyncapi.json
38
38
AudioConfiguration :
@@ -165,7 +165,7 @@ types:
165
165
166
166
Once this message is sent, EVI will not respond until a [Resume
167
167
Assistant
168
- message](/reference/empathic-voice-interface -evi/chat/chat #send.ResumeAssistantMessage.type )
168
+ message](/reference/speech-to-speech -evi/chat#send.ResumeAssistantMessage)
169
169
is sent. When paused, EVI won't respond, but transcriptions of your
170
170
audio inputs will still be recorded.
171
171
custom_session_id :
@@ -228,7 +228,7 @@ types:
228
228
229
229
230
230
For more information, please refer to the [Session Settings
231
- guide](/docs/empathic-voice-interface -evi/configuration/session-settings).
231
+ guide](/docs/speech-to-speech -evi/configuration/session-settings).
232
232
custom_session_id :
233
233
type : optional<string>
234
234
docs : >-
@@ -245,8 +245,8 @@ types:
245
245
It is recommended to pass a `custom_session_id` if you are using a
246
246
Custom Language Model. Please see our guide to [using a custom
247
247
language
248
- model](/docs/empathic-voice-interface -evi/guides/custom-language-model)
249
- with EVI to learn more.
248
+ model](/docs/speech-to-speech -evi/guides/custom-language-model) with
249
+ EVI to learn more.
250
250
system_prompt :
251
251
type : optional<string>
252
252
docs : >-
@@ -268,7 +268,7 @@ types:
268
268
269
269
270
270
For help writing a system prompt, see our [Prompting
271
- Guide](/docs/empathic-voice-interface -evi/guides/prompting).
271
+ Guide](/docs/speech-to-speech -evi/guides/prompting).
272
272
context :
273
273
type : optional<Context>
274
274
docs : >-
@@ -294,7 +294,7 @@ types:
294
294
in PCM Linear 16 (16-bit, little-endian, signed PCM WAV data). For
295
295
detailed instructions on how to configure session settings for PCM
296
296
Linear 16 audio, please refer to the [Session Settings
297
- guide](/docs/empathic-voice-interface -evi/configuration/session-settings).
297
+ guide](/docs/speech-to-speech -evi/configuration/session-settings).
298
298
language_model_api_key :
299
299
type : optional<string>
300
300
docs : >-
@@ -314,7 +314,7 @@ types:
314
314
searching the web or calling external APIs. Built-in tools, like web
315
315
search, are natively integrated, while user-defined tools are created
316
316
and invoked by the user. To learn more, see our [Tool Use
317
- Guide](/docs/empathic-voice-interface -evi/features/tool-use).
317
+ Guide](/docs/speech-to-speech -evi/features/tool-use).
318
318
builtin_tools :
319
319
type : optional<list<BuiltinToolConfig>>
320
320
docs : >-
@@ -325,7 +325,7 @@ types:
325
325
searching the web or calling external APIs. Built-in tools, like web
326
326
search, are natively integrated, while user-defined tools are created
327
327
and invoked by the user. To learn more, see our [Tool Use
328
- Guide](/docs/empathic-voice-interface -evi/features/tool-use).
328
+ Guide](/docs/speech-to-speech -evi/features/tool-use).
329
329
330
330
331
331
Currently, the only built-in tool Hume provides is **Web Search**.
@@ -350,7 +350,7 @@ types:
350
350
Using this field, you can personalize responses based on
351
351
session-specific details. For more guidance, see our [guide on using
352
352
dynamic
353
- variables](/docs/empathic-voice-interface -evi/features/dynamic-variables).
353
+ variables](/docs/speech-to-speech -evi/features/dynamic-variables).
354
354
source :
355
355
openapi : evi-asyncapi.json
356
356
Tool :
@@ -395,7 +395,7 @@ types:
395
395
396
396
397
397
Upon receiving a [Tool Call
398
- message](/reference/empathic-voice-interface -evi/chat/chat #receive.ToolCallMessage.type )
398
+ message](/reference/speech-to-speech -evi/chat#receive.ToolCallMessage)
399
399
and failing to invoke the function, this message is sent to notify EVI
400
400
of the tool's failure.
401
401
custom_session_id :
@@ -418,7 +418,7 @@ types:
418
418
invocation, ensuring that the Tool Error message is linked to the
419
419
appropriate tool call request. The specified `tool_call_id` must match
420
420
the one received in the [Tool Call
421
- message](/reference/empathic-voice-interface -evi/chat/chat #receive.ToolCallMessage.type ).
421
+ message](/reference/speech-to-speech -evi/chat#receive.ToolCallMessage).
422
422
content :
423
423
type : optional<string>
424
424
docs : >-
@@ -449,7 +449,7 @@ types:
449
449
450
450
451
451
Upon receiving a [Tool Call
452
- message](/reference/empathic-voice-interface -evi/chat/chat #receive.ToolCallMessage.type )
452
+ message](/reference/speech-to-speech -evi/chat#receive.ToolCallMessage)
453
453
and successfully invoking the function, this message is sent to convey
454
454
the result of the function call back to EVI.
455
455
custom_session_id :
@@ -467,7 +467,7 @@ types:
467
467
invocation, ensuring that the correct response is linked to the
468
468
appropriate request. The specified `tool_call_id` must match the one
469
469
received in the [Tool Call
470
- message](/reference/empathic-voice-interface -evi/chat /chat#receive.ToolCallMessage.tool_call_id).
470
+ message](/reference/speech-to-speech -evi/chat#receive.ToolCallMessage.tool_call_id).
471
471
content :
472
472
type : string
473
473
docs : >-
@@ -482,7 +482,7 @@ types:
482
482
Include this optional field to help the supplemental LLM identify
483
483
which tool generated the response. The specified `tool_name` must
484
484
match the one received in the [Tool Call
485
- message](/reference/empathic-voice-interface -evi/chat/chat #receive.ToolCallMessage.type ).
485
+ message](/reference/speech-to-speech -evi/chat#receive.ToolCallMessage).
486
486
tool_type :
487
487
type : optional<ToolType>
488
488
docs : >-
@@ -584,7 +584,7 @@ types:
584
584
docs : >-
585
585
Indicates if this message was inserted into the conversation as text
586
586
from an [Assistant Input
587
- message](/reference/empathic-voice-interface -evi/chat /chat#send.AssistantInput.text).
587
+ message](/reference/speech-to-speech -evi/chat#send.AssistantInput.text).
588
588
source :
589
589
openapi : evi-asyncapi.json
590
590
AssistantProsody :
@@ -693,14 +693,14 @@ types:
693
693
694
694
695
695
Used to resume a Chat when passed in the
696
- [resumed_chat_group_id](/reference/empathic-voice-interface -evi/chat /chat#request.query.resumed_chat_group_id)
696
+ [resumed_chat_group_id](/reference/speech-to-speech -evi/chat#request.query.resumed_chat_group_id)
697
697
query parameter of a subsequent connection request. This allows EVI to
698
698
continue the conversation from where it left off within the Chat
699
699
Group.
700
700
701
701
702
702
Learn more about [supporting chat
703
- resumability](/docs/empathic-voice-interface -evi/faq#does-evi-support-chat-resumability)
703
+ resumability](/docs/speech-to-speech -evi/faq#does-evi-support-chat-resumability)
704
704
from the EVI FAQ.
705
705
chat_id :
706
706
type : string
@@ -897,9 +897,9 @@ types:
897
897
docs : >-
898
898
Indicates whether a response to the tool call is required from the
899
899
developer, either in the form of a [Tool Response
900
- message](/reference/empathic-voice-interface -evi/chat/chat #send.ToolResponseMessage.type )
900
+ message](/reference/speech-to-speech -evi/chat#send.ToolResponseMessage)
901
901
or a [Tool Error
902
- message](/reference/empathic-voice-interface -evi/chat/chat #send.ToolErrorMessage.type ).
902
+ message](/reference/speech-to-speech -evi/chat#send.ToolErrorMessage).
903
903
source :
904
904
openapi : evi-asyncapi.json
905
905
UserInterruption :
@@ -939,12 +939,10 @@ types:
939
939
940
940
This message contains both a transcript of the user's input and the
941
941
expression measurement predictions if the input was sent as an [Audio
942
- Input
943
- message](/reference/empathic-voice-interface-evi/chat/chat#send.AudioInput.type).
942
+ Input message](/reference/speech-to-speech-evi/chat#send.AudioInput).
944
943
Expression measurement predictions are not provided for a [User Input
945
- message](/reference/empathic-voice-interface-evi/chat/chat#send.UserInput.type),
946
- as the prosody model relies on audio input and cannot process text
947
- alone.
944
+ message](/reference/speech-to-speech-evi/chat#send.UserInput), as the
945
+ prosody model relies on audio input and cannot process text alone.
948
946
custom_session_id :
949
947
type : optional<string>
950
948
docs : >-
@@ -964,7 +962,7 @@ types:
964
962
docs : >-
965
963
Indicates if this message was inserted into the conversation as text
966
964
from a [User
967
- Input](/reference/empathic-voice-interface -evi/chat /chat#send.UserInput.text)
965
+ Input](/reference/speech-to-speech -evi/chat#send.UserInput.text)
968
966
message.
969
967
interim :
970
968
type : boolean
@@ -981,7 +979,7 @@ types:
981
979
982
980
983
981
Interim transcripts are only sent when the
984
- [`verbose_transcription`](/reference/empathic-voice-interface -evi/chat /chat#request.query.verbose_transcription)
982
+ [`verbose_transcription`](/reference/speech-to-speech -evi/chat#request.query.verbose_transcription)
985
983
query parameter is set to `true` in the initial handshake.
986
984
source :
987
985
openapi : evi-asyncapi.json
0 commit comments