openai 0.91.0 → 0.93.0

data/sig/openai/models/realtime/realtime_session.rbs

@@ -26,94 +26,307 @@ module OpenAI
         }
 
       class RealtimeSession < OpenAI::Internal::Type::BaseModel
+        # Unique identifier for the session that looks like `sess_1234567890abcdef`.
         attr_reader id: String?
 
+        # Unique identifier for the session that looks like `sess_1234567890abcdef`.
         def id=: (String) -> String
 
+        # Expiration timestamp for the session, in seconds since epoch.
         attr_reader expires_at: Integer?
 
+        # Expiration timestamp for the session, in seconds since epoch.
         def expires_at=: (Integer) -> Integer
 
+        # Additional fields to include in server outputs.
+        #
+        # - `item.input_audio_transcription.logprobs`: Include logprobs for input audio
+        #   transcription.
         attr_accessor include: ::Array[OpenAI::Models::Realtime::RealtimeSession::include_]?
 
+        # The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For
+        # `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, single channel
+        # (mono), and little-endian byte order.
         attr_reader input_audio_format: OpenAI::Models::Realtime::RealtimeSession::input_audio_format?
 
+        # The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For
+        # `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, single channel
+        # (mono), and little-endian byte order.
         def input_audio_format=: (
           OpenAI::Models::Realtime::RealtimeSession::input_audio_format
         ) -> OpenAI::Models::Realtime::RealtimeSession::input_audio_format
 
+        # Configuration for input audio noise reduction. This can be set to `null` to turn
+        # off. Noise reduction filters audio added to the input audio buffer before it is
+        # sent to VAD and the model. Filtering the audio can improve VAD and turn
+        # detection accuracy (reducing false positives) and model performance by improving
+        # perception of the input audio.
         attr_reader input_audio_noise_reduction: OpenAI::Realtime::RealtimeSession::InputAudioNoiseReduction?
 
+        # Configuration for input audio noise reduction. This can be set to `null` to turn
+        # off. Noise reduction filters audio added to the input audio buffer before it is
+        # sent to VAD and the model. Filtering the audio can improve VAD and turn
+        # detection accuracy (reducing false positives) and model performance by improving
+        # perception of the input audio.
         def input_audio_noise_reduction=: (
           OpenAI::Realtime::RealtimeSession::InputAudioNoiseReduction
         ) -> OpenAI::Realtime::RealtimeSession::InputAudioNoiseReduction
 
+        # Configuration for input audio transcription, defaults to off and can be set to
+        # `null` to turn off once on. Input audio transcription is not native to the
+        # model, since the model consumes audio directly. Transcription runs
+        # asynchronously through
+        # [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
+        # and should be treated as guidance of input audio content rather than precisely
+        # what the model heard. The client can optionally set the language and prompt for
+        # transcription, these offer additional guidance to the transcription service.
         attr_accessor input_audio_transcription: OpenAI::Realtime::AudioTranscription?
 
+        # The default system instructions (i.e. system message) prepended to model calls.
+        # This field allows the client to guide the model on desired responses. The model
+        # can be instructed on response content and format, (e.g. "be extremely succinct",
+        # "act friendly", "here are examples of good responses") and on audio behavior
+        # (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The
+        # instructions are not guaranteed to be followed by the model, but they provide
+        # guidance to the model on the desired behavior.
+        #
+        # Note that the server sets default instructions which will be used if this field
+        # is not set and are visible in the `session.created` event at the start of the
+        # session.
         attr_reader instructions: String?
 
+        # The default system instructions (i.e. system message) prepended to model calls.
+        # This field allows the client to guide the model on desired responses. The model
+        # can be instructed on response content and format, (e.g. "be extremely succinct",
+        # "act friendly", "here are examples of good responses") and on audio behavior
+        # (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The
+        # instructions are not guaranteed to be followed by the model, but they provide
+        # guidance to the model on the desired behavior.
+        #
+        # Note that the server sets default instructions which will be used if this field
+        # is not set and are visible in the `session.created` event at the start of the
+        # session.
         def instructions=: (String) -> String
 
+        # Maximum number of output tokens for a single assistant response, inclusive of
+        # tool calls. Provide an integer between 1 and 4096 to limit output tokens, or
+        # `inf` for the maximum available tokens for a given model. Defaults to `inf`.
         attr_reader max_response_output_tokens: OpenAI::Models::Realtime::RealtimeSession::max_response_output_tokens?
 
+        # Maximum number of output tokens for a single assistant response, inclusive of
+        # tool calls. Provide an integer between 1 and 4096 to limit output tokens, or
+        # `inf` for the maximum available tokens for a given model. Defaults to `inf`.
         def max_response_output_tokens=: (
           OpenAI::Models::Realtime::RealtimeSession::max_response_output_tokens
         ) -> OpenAI::Models::Realtime::RealtimeSession::max_response_output_tokens
 
+        # The set of modalities the model can respond with. To disable audio, set this to
+        # ["text"].
         attr_reader modalities: ::Array[OpenAI::Models::Realtime::RealtimeSession::modality]?
 
+        # The set of modalities the model can respond with. To disable audio, set this to
+        # ["text"].
         def modalities=: (
           ::Array[OpenAI::Models::Realtime::RealtimeSession::modality]
         ) -> ::Array[OpenAI::Models::Realtime::RealtimeSession::modality]
 
+        # The Realtime model used for this session.
         attr_reader model: OpenAI::Models::Realtime::RealtimeSession::model?
 
+        # The Realtime model used for this session.
         def model=: (
           OpenAI::Models::Realtime::RealtimeSession::model
         ) -> OpenAI::Models::Realtime::RealtimeSession::model
 
+        # The object type. Always `realtime.session`.
         attr_reader object: OpenAI::Models::Realtime::RealtimeSession::object?
 
+        # The object type. Always `realtime.session`.
         def object=: (
           OpenAI::Models::Realtime::RealtimeSession::object
         ) -> OpenAI::Models::Realtime::RealtimeSession::object
 
+        # The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+        # For `pcm16`, output audio is sampled at a rate of 24kHz.
         attr_reader output_audio_format: OpenAI::Models::Realtime::RealtimeSession::output_audio_format?
 
+        # The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+        # For `pcm16`, output audio is sampled at a rate of 24kHz.
         def output_audio_format=: (
           OpenAI::Models::Realtime::RealtimeSession::output_audio_format
         ) -> OpenAI::Models::Realtime::RealtimeSession::output_audio_format
 
+        # Reference to a prompt template and its variables.
+        # [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).
         attr_accessor prompt: OpenAI::Responses::ResponsePrompt?
 
+        # The speed of the model's spoken response. 1.0 is the default speed. 0.25 is the
+        # minimum speed. 1.5 is the maximum speed. This value can only be changed in
+        # between model turns, not while a response is in progress.
         attr_reader speed: Float?
 
+        # The speed of the model's spoken response. 1.0 is the default speed. 0.25 is the
+        # minimum speed. 1.5 is the maximum speed. This value can only be changed in
+        # between model turns, not while a response is in progress.
         def speed=: (Float) -> Float
 
+        # Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a
+        # temperature of 0.8 is highly recommended for best performance.
         attr_reader temperature: Float?
 
+        # Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a
+        # temperature of 0.8 is highly recommended for best performance.
         def temperature=: (Float) -> Float
 
+        # How the model chooses tools. Options are `auto`, `none`, `required`, or specify
+        # a function.
         attr_reader tool_choice: String?
 
+        # How the model chooses tools. Options are `auto`, `none`, `required`, or specify
+        # a function.
         def tool_choice=: (String) -> String
 
+        # Tools (functions) available to the model.
         attr_reader tools: ::Array[OpenAI::Realtime::RealtimeFunctionTool]?
 
+        # Tools (functions) available to the model.
         def tools=: (
           ::Array[OpenAI::Realtime::RealtimeFunctionTool]
         ) -> ::Array[OpenAI::Realtime::RealtimeFunctionTool]
 
+        # Configuration options for tracing. Set to null to disable tracing. Once tracing
+        # is enabled for a session, the configuration cannot be modified.
+        #
+        # `auto` will create a trace for the session with default values for the workflow
+        # name, group id, and metadata.
         attr_accessor tracing: OpenAI::Models::Realtime::RealtimeSession::tracing?
 
+        # Configuration for turn detection, ether Server VAD or Semantic VAD. This can be
+        # set to `null` to turn off, in which case the client must manually trigger model
+        # response.
+        #
+        # Server VAD means that the model will detect the start and end of speech based on
+        # audio volume and respond at the end of user speech.
+        #
+        # Semantic VAD is more advanced and uses a turn detection model (in conjunction
+        # with VAD) to semantically estimate whether the user has finished speaking, then
+        # dynamically sets a timeout based on this probability. For example, if user audio
+        # trails off with "uhhm", the model will score a low probability of turn end and
+        # wait longer for the user to continue speaking. This can be useful for more
+        # natural conversations, but may have a higher latency.
+        #
+        # For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+        # `null`; VAD is not supported.
         attr_accessor turn_detection: OpenAI::Models::Realtime::RealtimeSession::turn_detection?
 
+        # The voice the model uses to respond. Voice cannot be changed during the session
+        # once the model has responded with audio at least once. Current voice options are
+        # `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, and `verse`.
         attr_reader voice: OpenAI::Models::Realtime::RealtimeSession::voice?
 
+        # The voice the model uses to respond. Voice cannot be changed during the session
+        # once the model has responded with audio at least once. Current voice options are
+        # `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, and `verse`.
         def voice=: (
           OpenAI::Models::Realtime::RealtimeSession::voice
         ) -> OpenAI::Models::Realtime::RealtimeSession::voice
 
+        # @param id
+        #   Unique identifier for the session that looks like `sess_1234567890abcdef`.
+        # @param expires_at
+        #   Expiration timestamp for the session, in seconds since epoch.
+        # @param include
+        #   Additional fields to include in server outputs.
+        #
+        #   - `item.input_audio_transcription.logprobs`: Include logprobs for input audio
+        #     transcription.
+        # @param input_audio_format
+        #   The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. For
+        #   `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, single channel
+        #   (mono), and little-endian byte order.
+        # @param input_audio_noise_reduction
+        #   Configuration for input audio noise reduction. This can be set to `null` to turn
+        #   off. Noise reduction filters audio added to the input audio buffer before it is
+        #   sent to VAD and the model. Filtering the audio can improve VAD and turn
+        #   detection accuracy (reducing false positives) and model performance by improving
+        #   perception of the input audio.
+        # @param input_audio_transcription
+        #   Configuration for input audio transcription, defaults to off and can be set to
+        #   `null` to turn off once on. Input audio transcription is not native to the
+        #   model, since the model consumes audio directly. Transcription runs
+        #   asynchronously through
+        #   [the /audio/transcriptions endpoint](https://developers.openai.com/api/reference/resources/audio/subresources/transcriptions/methods/create)
+        #   and should be treated as guidance of input audio content rather than precisely
+        #   what the model heard. The client can optionally set the language and prompt for
+        #   transcription, these offer additional guidance to the transcription service.
+        # @param instructions
+        #   The default system instructions (i.e. system message) prepended to model calls.
+        #   This field allows the client to guide the model on desired responses. The model
+        #   can be instructed on response content and format, (e.g. "be extremely succinct",
+        #   "act friendly", "here are examples of good responses") and on audio behavior
+        #   (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The
+        #   instructions are not guaranteed to be followed by the model, but they provide
+        #   guidance to the model on the desired behavior.
+        #
+        #   Note that the server sets default instructions which will be used if this field
+        #   is not set and are visible in the `session.created` event at the start of the
+        #   session.
+        # @param max_response_output_tokens
+        #   Maximum number of output tokens for a single assistant response, inclusive of
+        #   tool calls. Provide an integer between 1 and 4096 to limit output tokens, or
+        #   `inf` for the maximum available tokens for a given model. Defaults to `inf`.
+        # @param modalities
+        #   The set of modalities the model can respond with. To disable audio, set this to
+        #   ["text"].
+        # @param model
+        #   The Realtime model used for this session.
+        # @param object
+        #   The object type. Always `realtime.session`.
+        # @param output_audio_format
+        #   The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+        #   For `pcm16`, output audio is sampled at a rate of 24kHz.
+        # @param prompt
+        #   Reference to a prompt template and its variables.
+        #   [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).
+        # @param speed
+        #   The speed of the model's spoken response. 1.0 is the default speed. 0.25 is the
+        #   minimum speed. 1.5 is the maximum speed. This value can only be changed in
+        #   between model turns, not while a response is in progress.
+        # @param temperature
+        #   Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a
+        #   temperature of 0.8 is highly recommended for best performance.
+        # @param tool_choice
+        #   How the model chooses tools. Options are `auto`, `none`, `required`, or specify
+        #   a function.
+        # @param tools
+        #   Tools (functions) available to the model.
+        # @param tracing
+        #   Configuration options for tracing. Set to null to disable tracing. Once tracing
+        #   is enabled for a session, the configuration cannot be modified.
+        #
+        #   `auto` will create a trace for the session with default values for the workflow
+        #   name, group id, and metadata.
+        # @param turn_detection
+        #   Configuration for turn detection, ether Server VAD or Semantic VAD. This can be
+        #   set to `null` to turn off, in which case the client must manually trigger model
+        #   response.
+        #
+        #   Server VAD means that the model will detect the start and end of speech based on
+        #   audio volume and respond at the end of user speech.
+        #
+        #   Semantic VAD is more advanced and uses a turn detection model (in conjunction
+        #   with VAD) to semantically estimate whether the user has finished speaking, then
+        #   dynamically sets a timeout based on this probability. For example, if user audio
+        #   trails off with "uhhm", the model will score a low probability of turn end and
+        #   wait longer for the user to continue speaking. This can be useful for more
+        #   natural conversations, but may have a higher latency.
+        #
+        #   For `gpt-realtime-whisper` transcription sessions, turn detection must be set to
+        #   `null`; VAD is not supported.
+        # @param voice
+        #   The voice the model uses to respond. Voice cannot be changed during the session
+        #   once the model has responded with audio at least once. Current voice options are
+        #   `alloy`, `ash`, `ballad`, `coral`, `echo`, `sage`, `shimmer`, and `verse`.
         def initialize: (
           ?id: String,
           ?expires_at: Integer,
@@ -186,12 +399,22 @@ module OpenAI
           { ?type: OpenAI::Models::Realtime::noise_reduction_type }
 
         class InputAudioNoiseReduction < OpenAI::Internal::Type::BaseModel
+          # Type of noise reduction. `near_field` is for close-talking microphones such as
+          # headphones, `far_field` is for far-field microphones such as laptop or
+          # conference room microphones.
           attr_reader type: OpenAI::Models::Realtime::noise_reduction_type?
 
+          # Type of noise reduction. `near_field` is for close-talking microphones such as
+          # headphones, `far_field` is for far-field microphones such as laptop or
+          # conference room microphones.
           def type=: (
             OpenAI::Models::Realtime::noise_reduction_type
           ) -> OpenAI::Models::Realtime::noise_reduction_type
 
+          # @param type
+          #   Type of noise reduction. `near_field` is for close-talking microphones such as
+          #   headphones, `far_field` is for far-field microphones such as laptop or
+          #   conference room microphones.
           def initialize: (
             ?type: OpenAI::Models::Realtime::noise_reduction_type
           ) -> void
@@ -295,18 +518,39 @@ module OpenAI
             { ?group_id: String, ?metadata: top, ?workflow_name: String }
 
           class TracingConfiguration < OpenAI::Internal::Type::BaseModel
+            # The group id to attach to this trace to enable filtering and grouping in the
+            # traces dashboard.
             attr_reader group_id: String?
 
+            # The group id to attach to this trace to enable filtering and grouping in the
+            # traces dashboard.
             def group_id=: (String) -> String
 
+            # The arbitrary metadata to attach to this trace to enable filtering in the traces
+            # dashboard.
             attr_reader metadata: top?
 
+            # The arbitrary metadata to attach to this trace to enable filtering in the traces
+            # dashboard.
             def metadata=: (top) -> top
 
+            # The name of the workflow to attach to this trace. This is used to name the trace
+            # in the traces dashboard.
             attr_reader workflow_name: String?
 
+            # The name of the workflow to attach to this trace. This is used to name the trace
+            # in the traces dashboard.
             def workflow_name=: (String) -> String
 
+            # @param group_id
+            #   The group id to attach to this trace to enable filtering and grouping in the
+            #   traces dashboard.
+            # @param metadata
+            #   The arbitrary metadata to attach to this trace to enable filtering in the traces
+            #   dashboard.
+            # @param workflow_name
+            #   The name of the workflow to attach to this trace. This is used to name the trace
+            #   in the traces dashboard.
             def initialize: (
               ?group_id: String,
               ?metadata: top,
@@ -342,30 +586,126 @@ module OpenAI
             }
 
           class ServerVad < OpenAI::Internal::Type::BaseModel
+            # Type of turn detection, `server_vad` to turn on simple Server VAD.
             attr_accessor type: :server_vad
 
+            # Whether or not to automatically generate a response when a VAD stop event
+            # occurs. If `interrupt_response` is set to `false` this may fail to create a
+            # response if the model is already responding.
+            #
+            # If both `create_response` and `interrupt_response` are set to `false`, the model
+            # will never respond automatically but VAD events will still be emitted.
             attr_reader create_response: bool?
 
+            # Whether or not to automatically generate a response when a VAD stop event
+            # occurs. If `interrupt_response` is set to `false` this may fail to create a
+            # response if the model is already responding.
+            #
+            # If both `create_response` and `interrupt_response` are set to `false`, the model
+            # will never respond automatically but VAD events will still be emitted.
             def create_response=: (bool) -> bool
 
+            # Optional timeout after which a model response will be triggered automatically.
+            # This is useful for situations in which a long pause from the user is unexpected,
+            # such as a phone call. The model will effectively prompt the user to continue the
+            # conversation based on the current context.
+            #
+            # The timeout value will be applied after the last model response's audio has
+            # finished playing, i.e. it's set to the `response.done` time plus audio playback
+            # duration.
+            #
+            # An `input_audio_buffer.timeout_triggered` event (plus events associated with the
+            # Response) will be emitted when the timeout is reached. Idle timeout is currently
+            # only supported for `server_vad` mode.
             attr_accessor idle_timeout_ms: Integer?
 
+            # Whether or not to automatically interrupt (cancel) any ongoing response with
+            # output to the default conversation (i.e. `conversation` of `auto`) when a VAD
+            # start event occurs. If `true` then the response will be cancelled, otherwise it
+            # will continue until complete.
+            #
+            # If both `create_response` and `interrupt_response` are set to `false`, the model
+            # will never respond automatically but VAD events will still be emitted.
             attr_reader interrupt_response: bool?
 
+            # Whether or not to automatically interrupt (cancel) any ongoing response with
+            # output to the default conversation (i.e. `conversation` of `auto`) when a VAD
+            # start event occurs. If `true` then the response will be cancelled, otherwise it
+            # will continue until complete.
+            #
+            # If both `create_response` and `interrupt_response` are set to `false`, the model
+            # will never respond automatically but VAD events will still be emitted.
             def interrupt_response=: (bool) -> bool
 
+            # Used only for `server_vad` mode. Amount of audio to include before the VAD
+            # detected speech (in milliseconds). Defaults to 300ms.
             attr_reader prefix_padding_ms: Integer?
 
+            # Used only for `server_vad` mode. Amount of audio to include before the VAD
+            # detected speech (in milliseconds). Defaults to 300ms.
             def prefix_padding_ms=: (Integer) -> Integer
 
+            # Used only for `server_vad` mode. Duration of silence to detect speech stop (in
+            # milliseconds). Defaults to 500ms. With shorter values the model will respond
+            # more quickly, but may jump in on short pauses from the user.
             attr_reader silence_duration_ms: Integer?
 
+            # Used only for `server_vad` mode. Duration of silence to detect speech stop (in
+            # milliseconds). Defaults to 500ms. With shorter values the model will respond
+            # more quickly, but may jump in on short pauses from the user.
             def silence_duration_ms=: (Integer) -> Integer
 
+            # Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this
+            # defaults to 0.5. A higher threshold will require louder audio to activate the
+            # model, and thus might perform better in noisy environments.
             attr_reader threshold: Float?
 
+            # Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this
+            # defaults to 0.5. A higher threshold will require louder audio to activate the
+            # model, and thus might perform better in noisy environments.
             def threshold=: (Float) -> Float
 
+            # @param create_response
+            #   Whether or not to automatically generate a response when a VAD stop event
+            #   occurs. If `interrupt_response` is set to `false` this may fail to create a
+            #   response if the model is already responding.
+            #
+            #   If both `create_response` and `interrupt_response` are set to `false`, the model
+            #   will never respond automatically but VAD events will still be emitted.
+            # @param idle_timeout_ms
+            #   Optional timeout after which a model response will be triggered automatically.
+            #   This is useful for situations in which a long pause from the user is unexpected,
+            #   such as a phone call. The model will effectively prompt the user to continue the
+            #   conversation based on the current context.
+            #
+            #   The timeout value will be applied after the last model response's audio has
+            #   finished playing, i.e. it's set to the `response.done` time plus audio playback
+            #   duration.
+            #
+            #   An `input_audio_buffer.timeout_triggered` event (plus events associated with the
+            #   Response) will be emitted when the timeout is reached. Idle timeout is currently
+            #   only supported for `server_vad` mode.
+            # @param interrupt_response
+            #   Whether or not to automatically interrupt (cancel) any ongoing response with
+            #   output to the default conversation (i.e. `conversation` of `auto`) when a VAD
+            #   start event occurs. If `true` then the response will be cancelled, otherwise it
+            #   will continue until complete.
+            #
+            #   If both `create_response` and `interrupt_response` are set to `false`, the model
+            #   will never respond automatically but VAD events will still be emitted.
+            # @param prefix_padding_ms
+            #   Used only for `server_vad` mode. Amount of audio to include before the VAD
+            #   detected speech (in milliseconds). Defaults to 300ms.
+            # @param silence_duration_ms
+            #   Used only for `server_vad` mode. Duration of silence to detect speech stop (in
+            #   milliseconds). Defaults to 500ms. With shorter values the model will respond
+            #   more quickly, but may jump in on short pauses from the user.
+            # @param threshold
+            #   Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this
+            #   defaults to 0.5. A higher threshold will require louder audio to activate the
+            #   model, and thus might perform better in noisy environments.
+            # @param type
+            #   Type of turn detection, `server_vad` to turn on simple Server VAD.
             def initialize: (
               ?create_response: bool,
               ?idle_timeout_ms: Integer?,
@@ -396,22 +736,55 @@ module OpenAI
             }
 
           class SemanticVad < OpenAI::Internal::Type::BaseModel
+            # Type of turn detection, `semantic_vad` to turn on Semantic VAD.
             attr_accessor type: :semantic_vad
 
+            # Whether or not to automatically generate a response when a VAD stop event
+            # occurs.
             attr_reader create_response: bool?
 
+            # Whether or not to automatically generate a response when a VAD stop event
+            # occurs.
             def create_response=: (bool) -> bool
 
+            # Used only for `semantic_vad` mode. The eagerness of the model to respond. `low`
+            # will wait longer for the user to continue speaking, `high` will respond more
+            # quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`,
+            # and `high` have max timeouts of 8s, 4s, and 2s respectively.
             attr_reader eagerness: OpenAI::Models::Realtime::RealtimeSession::TurnDetection::SemanticVad::eagerness?
 
+            # Used only for `semantic_vad` mode. The eagerness of the model to respond. `low`
+            # will wait longer for the user to continue speaking, `high` will respond more
+            # quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`,
+            # and `high` have max timeouts of 8s, 4s, and 2s respectively.
             def eagerness=: (
               OpenAI::Models::Realtime::RealtimeSession::TurnDetection::SemanticVad::eagerness
             ) -> OpenAI::Models::Realtime::RealtimeSession::TurnDetection::SemanticVad::eagerness
 
+            # Whether or not to automatically interrupt any ongoing response with output to
+            # the default conversation (i.e. `conversation` of `auto`) when a VAD start event
+            # occurs.
             attr_reader interrupt_response: bool?
 
+            # Whether or not to automatically interrupt any ongoing response with output to
+            # the default conversation (i.e. `conversation` of `auto`) when a VAD start event
+            # occurs.
             def interrupt_response=: (bool) -> bool
 
+            # @param create_response
+            #   Whether or not to automatically generate a response when a VAD stop event
+            #   occurs.
+            # @param eagerness
+            #   Used only for `semantic_vad` mode. The eagerness of the model to respond. `low`
+            #   will wait longer for the user to continue speaking, `high` will respond more
+            #   quickly. `auto` is the default and is equivalent to `medium`. `low`, `medium`,
+            #   and `high` have max timeouts of 8s, 4s, and 2s respectively.
+            # @param interrupt_response
+            #   Whether or not to automatically interrupt any ongoing response with output to
+            #   the default conversation (i.e. `conversation` of `auto`) when a VAD start event
+            #   occurs.
+            # @param type
+            #   Type of turn detection, `semantic_vad` to turn on Semantic VAD.
             def initialize: (
               ?create_response: bool,
               ?eagerness: OpenAI::Models::Realtime::RealtimeSession::TurnDetection::SemanticVad::eagerness,