@@ -98,17 +98,111 @@ channel:
9898 Use the GET `/v0/evi/chat_groups` endpoint to obtain the Chat Group IDs
9999 of all Chat Groups associated with an API key. This endpoint returns a
100100 list of all available chat groups.
101- session_settings[audio][channels] : optional<integer>
102- session_settings[audio][encoding] : optional<string>
103- session_settings[audio][sample_rate] : optional<integer>
104- session_settings[context][text] : optional<string>
105- session_settings[context][type] : optional<string>
106- session_settings[custom_session_id] : optional<string>
107- session_settings[event_limit] : optional<integer>
108- session_settings[language_model_api_key] : optional<string>
109- session_settings[system_prompt] : optional<string>
110- session_settings[variables] : optional<string>
111- session_settings[voice_id] : optional<string>
101+ session_settings[audio][channels] :
102+ type : optional<integer>
103+ docs : Sets number of audio channels for audio input.
104+ session_settings[audio][encoding] :
105+ type : optional<string>
106+ docs : Sets encoding format of the audio input, such as `linear16`.
107+ session_settings[audio][sample_rate] :
108+ type : optional<integer>
109+ docs : >-
110+ Sets the sample rate for audio input. (Number of samples per second in
111+ the audio input, measured in Hertz.)
112+ session_settings[context][text] :
113+ type : optional<string>
114+ docs : >-
115+ The context to be injected into the conversation. Helps inform the LLM's
116+ response by providing relevant information about the ongoing
117+ conversation.
118+
119+
120+ This text will be appended to the end of
121+ [user_messages](/reference/speech-to-speech-evi/chat#receive.UserMessage.message.content)
122+ based on the chosen persistence level. For example, if you want to
123+ remind EVI of its role as a helpful weather assistant, the context you
124+ insert will be appended to the end of user messages as `{Context: You
125+ are a helpful weather assistant}`.
126+ session_settings[context][type] :
127+ type : optional<string>
128+ docs : >-
129+ The persistence level of the injected context. Specifies how long the
130+ injected context will remain active in the session.
131+
132+
133+ - **Temporary**: Context that is only applied to the following assistant
134+ response.
135+
136+
137+ - **Persistent**: Context that is applied to all subsequent assistant
138+ responses for the remainder of the Chat.
139+ session_settings[custom_session_id] :
140+ type : optional<string>
141+ docs : >-
142+ Used to manage conversational state, correlate frontend and backend
143+ data, and persist conversations across EVI sessions.
144+ session_settings[event_limit] :
145+ type : optional<integer>
146+ docs : >-
147+ The maximum number of chat events to return from chat history. By
148+ default, the system returns up to 300 events (100 events per page × 3
149+ pages). Set this parameter to a smaller value to limit the number of
150+ events returned.
151+ session_settings[language_model_api_key] :
152+ type : optional<string>
153+ docs : >-
154+ Third party API key for the supplemental language model.
155+
156+
157+ When provided, EVI will use this key instead of Hume's API key for the
158+ supplemental LLM. This allows you to bypass rate limits and utilize your
159+ own API key as needed.
160+ session_settings[system_prompt] :
161+ type : optional<string>
162+ docs : >-
163+ Instructions used to shape EVI's behavior, responses, and style for the
164+ session.
165+
166+
167+ When included in a Session Settings message, the provided Prompt
168+ overrides the existing one specified in the EVI configuration. If no
169+ Prompt was defined in the configuration, this Prompt will be the one
170+ used for the session.
171+
172+
173+ You can use the Prompt to define a specific goal or role for EVI,
174+ specifying how it should act or what it should focus on during the
175+ conversation. For example, EVI can be instructed to act as a customer
176+ support representative, a fitness coach, or a travel advisor, each with
177+ its own set of behaviors and response styles.
178+
179+
180+ For help writing a system prompt, see our [Prompting
181+ Guide](/docs/speech-to-speech-evi/guides/prompting).
182+ session_settings[variables] :
183+ type : optional<string>
184+ docs : >-
185+ This field allows you to assign values to dynamic variables referenced
186+ in your system prompt.
187+
188+
189+ Each key represents the variable name, and the corresponding value is
190+ the specific content you wish to assign to that variable within the
191+ session. While the values for variables can be strings, numbers, or
192+ booleans, the value will ultimately be converted to a string when
193+ injected into your system prompt.
194+
195+
196+ Using this field, you can personalize responses based on
197+ session-specific details. For more guidance, see our [guide on using
198+ dynamic
199+ variables](/docs/speech-to-speech-evi/features/dynamic-variables).
200+ session_settings[voice_id] :
201+ type : optional<string>
202+ docs : >-
203+ The name or ID of the voice from the `Voice Library` to be used as the
204+ speaker for this EVI session. This will override the speaker set in the
205+ selected configuration.
112206verbose_transcription :
113207 type : optional<boolean>
114208 default : false
![fern-api[bot]](https://avatars.githubusercontent.com/in/244756?v=4&size=40){kind=avatar}
0 commit comments