openai 0.20.0 → 0.21.0

data/lib/openai/models/realtime/realtime_audio_config.rb

@@ -0,0 +1,446 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeAudioConfig < OpenAI::Internal::Type::BaseModel
+        # @!attribute input
+        #
+        #   @return [OpenAI::Models::Realtime::RealtimeAudioConfig::Input, nil]
+        optional :input, -> { OpenAI::Realtime::RealtimeAudioConfig::Input }
+
+        # @!attribute output
+        #
+        #   @return [OpenAI::Models::Realtime::RealtimeAudioConfig::Output, nil]
+        optional :output, -> { OpenAI::Realtime::RealtimeAudioConfig::Output }
+
+        # @!method initialize(input: nil, output: nil)
+        #   Configuration for input and output audio.
+        #
+        #   @param input [OpenAI::Models::Realtime::RealtimeAudioConfig::Input]
+        #   @param output [OpenAI::Models::Realtime::RealtimeAudioConfig::Output]
+
+        # @see OpenAI::Models::Realtime::RealtimeAudioConfig#input
+        class Input < OpenAI::Internal::Type::BaseModel
+          # @!attribute 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.
+          #
+          #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Format, nil]
+          optional :format_,
+                   enum: -> {
+                     OpenAI::Realtime::RealtimeAudioConfig::Input::Format
+                   },
+                   api_name: :format
+
+          # @!attribute 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.
+          #
+          #   @return [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction, nil]
+          optional :noise_reduction, -> { OpenAI::Realtime::RealtimeAudioConfig::Input::NoiseReduction }
+
+          # @!attribute 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://platform.openai.com/docs/api-reference/audio/createTranscription)
+          #   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.
+          #
+          #   @return [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription, nil]
+          optional :transcription, -> { OpenAI::Realtime::RealtimeAudioConfig::Input::Transcription }
+
+          # @!attribute 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.
+          #
+          #   @return [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection, nil]
+          optional :turn_detection, -> { OpenAI::Realtime::RealtimeAudioConfig::Input::TurnDetection }
+
+          # @!method initialize(format_: nil, noise_reduction: nil, transcription: nil, turn_detection: nil)
+          #   Some parameter documentations has been truncated, see
+          #   {OpenAI::Models::Realtime::RealtimeAudioConfig::Input} for more details.
+          #
+          #   @param format_ [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Format] The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+          #
+          #   @param noise_reduction [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction] Configuration for input audio noise reduction. This can be set to `null` to turn
+          #
+          #   @param transcription [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription] Configuration for input audio transcription, defaults to off and can be set to `
+          #
+          #   @param turn_detection [OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection] Configuration for turn detection, ether Server VAD or Semantic VAD. This can be
+
+          # 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.
+          #
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input#format_
+          module Format
+            extend OpenAI::Internal::Type::Enum
+
+            PCM16 = :pcm16
+            G711_ULAW = :g711_ulaw
+            G711_ALAW = :g711_alaw
+
+            # @!method self.values
+            #   @return [Array<Symbol>]
+          end
+
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input#noise_reduction
+          class NoiseReduction < OpenAI::Internal::Type::BaseModel
+            # @!attribute 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.
+            #
+            #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction::Type, nil]
+            optional :type, enum: -> { OpenAI::Realtime::RealtimeAudioConfig::Input::NoiseReduction::Type }
+
+            # @!method initialize(type: nil)
+            #   Some parameter documentations has been truncated, see
+            #   {OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction} for more
+            #   details.
+            #
+            #   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 type [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction::Type] Type of noise reduction. `near_field` is for close-talking microphones such as h
+
+            # 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.
+            #
+            # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input::NoiseReduction#type
+            module Type
+              extend OpenAI::Internal::Type::Enum
+
+              NEAR_FIELD = :near_field
+              FAR_FIELD = :far_field
+
+              # @!method self.values
+              #   @return [Array<Symbol>]
+            end
+          end
+
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input#transcription
+          class Transcription < OpenAI::Internal::Type::BaseModel
+            # @!attribute language
+            #   The language of the input audio. Supplying the input language in
+            #   [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
+            #   format will improve accuracy and latency.
+            #
+            #   @return [String, nil]
+            optional :language, String
+
+            # @!attribute model
+            #   The model to use for transcription. Current options are `whisper-1`,
+            #   `gpt-4o-transcribe-latest`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe`, and
+            #   `gpt-4o-transcribe-diarize`.
+            #
+            #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription::Model, nil]
+            optional :model, enum: -> { OpenAI::Realtime::RealtimeAudioConfig::Input::Transcription::Model }
+
+            # @!attribute prompt
+            #   An optional text to guide the model's style or continue a previous audio
+            #   segment. For `whisper-1`, the
+            #   [prompt is a list of keywords](https://platform.openai.com/docs/guides/speech-to-text#prompting).
+            #   For `gpt-4o-transcribe` models, the prompt is a free text string, for example
+            #   "expect words related to technology".
+            #
+            #   @return [String, nil]
+            optional :prompt, String
+
+            # @!method initialize(language: nil, model: nil, prompt: nil)
+            #   Some parameter documentations has been truncated, see
+            #   {OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription} for more
+            #   details.
+            #
+            #   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://platform.openai.com/docs/api-reference/audio/createTranscription)
+            #   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 language [String] The language of the input audio. Supplying the input language in
+            #
+            #   @param model [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription::Model] The model to use for transcription. Current options are
+            #
+            #   @param prompt [String] An optional text to guide the model's style or continue a previous audio
+
+            # The model to use for transcription. Current options are `whisper-1`,
+            # `gpt-4o-transcribe-latest`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe`, and
+            # `gpt-4o-transcribe-diarize`.
+            #
+            # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input::Transcription#model
+            module Model
+              extend OpenAI::Internal::Type::Enum
+
+              WHISPER_1 = :"whisper-1"
+              GPT_4O_TRANSCRIBE_LATEST = :"gpt-4o-transcribe-latest"
+              GPT_4O_MINI_TRANSCRIBE = :"gpt-4o-mini-transcribe"
+              GPT_4O_TRANSCRIBE = :"gpt-4o-transcribe"
+              GPT_4O_TRANSCRIBE_DIARIZE = :"gpt-4o-transcribe-diarize"
+
+              # @!method self.values
+              #   @return [Array<Symbol>]
+            end
+          end
+
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input#turn_detection
+          class TurnDetection < OpenAI::Internal::Type::BaseModel
+            # @!attribute create_response
+            #   Whether or not to automatically generate a response when a VAD stop event
+            #   occurs.
+            #
+            #   @return [Boolean, nil]
+            optional :create_response, OpenAI::Internal::Type::Boolean
+
+            # @!attribute 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`.
+            #
+            #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection::Eagerness, nil]
+            optional :eagerness, enum: -> { OpenAI::Realtime::RealtimeAudioConfig::Input::TurnDetection::Eagerness }
+
+            # @!attribute idle_timeout_ms
+            #   Optional idle timeout after which turn detection will auto-timeout when no
+            #   additional audio is received.
+            #
+            #   @return [Integer, nil]
+            optional :idle_timeout_ms, Integer, nil?: true
+
+            # @!attribute 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.
+            #
+            #   @return [Boolean, nil]
+            optional :interrupt_response, OpenAI::Internal::Type::Boolean
+
+            # @!attribute prefix_padding_ms
+            #   Used only for `server_vad` mode. Amount of audio to include before the VAD
+            #   detected speech (in milliseconds). Defaults to 300ms.
+            #
+            #   @return [Integer, nil]
+            optional :prefix_padding_ms, Integer
+
+            # @!attribute 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.
+            #
+            #   @return [Integer, nil]
+            optional :silence_duration_ms, Integer
+
+            # @!attribute 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.
+            #
+            #   @return [Float, nil]
+            optional :threshold, Float
+
+            # @!attribute type
+            #   Type of turn detection.
+            #
+            #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection::Type, nil]
+            optional :type, enum: -> { OpenAI::Realtime::RealtimeAudioConfig::Input::TurnDetection::Type }
+
+            # @!method initialize(create_response: nil, eagerness: nil, idle_timeout_ms: nil, interrupt_response: nil, prefix_padding_ms: nil, silence_duration_ms: nil, threshold: nil, type: nil)
+            #   Some parameter documentations has been truncated, see
+            #   {OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection} for more
+            #   details.
+            #
+            #   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.
+            #
+            #   @param create_response [Boolean] Whether or not to automatically generate a response when a VAD stop event occurs
+            #
+            #   @param eagerness [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection::Eagerness] Used only for `semantic_vad` mode. The eagerness of the model to respond. `low`
+            #
+            #   @param idle_timeout_ms [Integer, nil] Optional idle timeout after which turn detection will auto-timeout when
+            #
+            #   @param interrupt_response [Boolean] Whether or not to automatically interrupt any ongoing response with output to th
+            #
+            #   @param prefix_padding_ms [Integer] Used only for `server_vad` mode. Amount of audio to include before the VAD detec
+            #
+            #   @param silence_duration_ms [Integer] Used only for `server_vad` mode. Duration of silence to detect speech stop (in m
+            #
+            #   @param threshold [Float] Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this
+            #
+            #   @param type [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection::Type] Type of turn detection.
+
+            # 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`.
+            #
+            # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection#eagerness
+            module Eagerness
+              extend OpenAI::Internal::Type::Enum
+
+              LOW = :low
+              MEDIUM = :medium
+              HIGH = :high
+              AUTO = :auto
+
+              # @!method self.values
+              #   @return [Array<Symbol>]
+            end
+
+            # Type of turn detection.
+            #
+            # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Input::TurnDetection#type
+            module Type
+              extend OpenAI::Internal::Type::Enum
+
+              SERVER_VAD = :server_vad
+              SEMANTIC_VAD = :semantic_vad
+
+              # @!method self.values
+              #   @return [Array<Symbol>]
+            end
+          end
+        end
+
+        # @see OpenAI::Models::Realtime::RealtimeAudioConfig#output
+        class Output < OpenAI::Internal::Type::BaseModel
+          # @!attribute 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.
+          #
+          #   @return [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Format, nil]
+          optional :format_,
+                   enum: -> {
+                     OpenAI::Realtime::RealtimeAudioConfig::Output::Format
+                   },
+                   api_name: :format
+
+          # @!attribute 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.
+          #
+          #   @return [Float, nil]
+          optional :speed, Float
+
+          # @!attribute 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`, `verse`, `marin`,
+          #   and `cedar`.
+          #
+          #   @return [String, Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice, nil]
+          optional :voice, union: -> { OpenAI::Realtime::RealtimeAudioConfig::Output::Voice }
+
+          # @!method initialize(format_: nil, speed: nil, voice: nil)
+          #   Some parameter documentations has been truncated, see
+          #   {OpenAI::Models::Realtime::RealtimeAudioConfig::Output} for more details.
+          #
+          #   @param format_ [Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Format] The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+          #
+          #   @param speed [Float] The speed of the model's spoken response. 1.0 is the default speed. 0.25 is
+          #
+          #   @param voice [String, Symbol, OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice] The voice the model uses to respond. Voice cannot be changed during the
+
+          # The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
+          # For `pcm16`, output audio is sampled at a rate of 24kHz.
+          #
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Output#format_
+          module Format
+            extend OpenAI::Internal::Type::Enum
+
+            PCM16 = :pcm16
+            G711_ULAW = :g711_ulaw
+            G711_ALAW = :g711_alaw
+
+            # @!method self.values
+            #   @return [Array<Symbol>]
+          end
+
+          # 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`, `verse`, `marin`,
+          # and `cedar`.
+          #
+          # @see OpenAI::Models::Realtime::RealtimeAudioConfig::Output#voice
+          module Voice
+            extend OpenAI::Internal::Type::Union
+
+            variant String
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::ALLOY }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::ASH }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::BALLAD }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::CORAL }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::ECHO }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::SAGE }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::SHIMMER }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::VERSE }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::MARIN }
+
+            variant const: -> { OpenAI::Models::Realtime::RealtimeAudioConfig::Output::Voice::CEDAR }
+
+            # @!method self.variants
+            #   @return [Array(String, Symbol)]
+
+            define_sorbet_constant!(:Variants) do
+              T.type_alias { T.any(String, OpenAI::Realtime::RealtimeAudioConfig::Output::Voice::TaggedSymbol) }
+            end
+
+            # @!group
+
+            ALLOY = :alloy
+            ASH = :ash
+            BALLAD = :ballad
+            CORAL = :coral
+            ECHO = :echo
+            SAGE = :sage
+            SHIMMER = :shimmer
+            VERSE = :verse
+            MARIN = :marin
+            CEDAR = :cedar
+
+            # @!endgroup
+          end
+        end
+      end
+    end
+  end
+end

data/lib/openai/models/realtime/realtime_client_event.rb

@@ -0,0 +1,123 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      # A realtime client event.
+      module RealtimeClientEvent
+        extend OpenAI::Internal::Type::Union
+
+        discriminator :type
+
+        # Add a new Item to the Conversation's context, including messages, function
+        # calls, and function call responses. This event can be used both to populate a
+        # "history" of the conversation and to add new items mid-stream, but has the
+        # current limitation that it cannot populate assistant audio messages.
+        #
+        # If successful, the server will respond with a `conversation.item.created`
+        # event, otherwise an `error` event will be sent.
+        variant :"conversation.item.create", -> { OpenAI::Realtime::ConversationItemCreateEvent }
+
+        # Send this event when you want to remove any item from the conversation
+        # history. The server will respond with a `conversation.item.deleted` event,
+        # unless the item does not exist in the conversation history, in which case the
+        # server will respond with an error.
+        variant :"conversation.item.delete", -> { OpenAI::Realtime::ConversationItemDeleteEvent }
+
+        # Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD.
+        # The server will respond with a `conversation.item.retrieved` event,
+        # unless the item does not exist in the conversation history, in which case the
+        # server will respond with an error.
+        variant :"conversation.item.retrieve", -> { OpenAI::Realtime::ConversationItemRetrieveEvent }
+
+        # Send this event to truncate a previous assistant message’s audio. The server
+        # will produce audio faster than realtime, so this event is useful when the user
+        # interrupts to truncate audio that has already been sent to the client but not
+        # yet played. This will synchronize the server's understanding of the audio with
+        # the client's playback.
+        #
+        # Truncating audio will delete the server-side text transcript to ensure there
+        # is not text in the context that hasn't been heard by the user.
+        #
+        # If successful, the server will respond with a `conversation.item.truncated`
+        # event.
+        variant :"conversation.item.truncate", -> { OpenAI::Realtime::ConversationItemTruncateEvent }
+
+        # Send this event to append audio bytes to the input audio buffer. The audio
+        # buffer is temporary storage you can write to and later commit. In Server VAD
+        # mode, the audio buffer is used to detect speech and the server will decide
+        # when to commit. When Server VAD is disabled, you must commit the audio buffer
+        # manually.
+        #
+        # The client may choose how much audio to place in each event up to a maximum
+        # of 15 MiB, for example streaming smaller chunks from the client may allow the
+        # VAD to be more responsive. Unlike made other client events, the server will
+        # not send a confirmation response to this event.
+        variant :"input_audio_buffer.append", -> { OpenAI::Realtime::InputAudioBufferAppendEvent }
+
+        # Send this event to clear the audio bytes in the buffer. The server will
+        # respond with an `input_audio_buffer.cleared` event.
+        variant :"input_audio_buffer.clear", -> { OpenAI::Realtime::InputAudioBufferClearEvent }
+
+        # **WebRTC Only:** Emit to cut off the current audio response. This will trigger the server to
+        # stop generating audio and emit a `output_audio_buffer.cleared` event. This
+        # event should be preceded by a `response.cancel` client event to stop the
+        # generation of the current response.
+        # [Learn more](https://platform.openai.com/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc).
+        variant :"output_audio_buffer.clear", -> { OpenAI::Realtime::OutputAudioBufferClearEvent }
+
+        # Send this event to commit the user input audio buffer, which will create a
+        # new user message item in the conversation. This event will produce an error
+        # if the input audio buffer is empty. When in Server VAD mode, the client does
+        # not need to send this event, the server will commit the audio buffer
+        # automatically.
+        #
+        # Committing the input audio buffer will trigger input audio transcription
+        # (if enabled in session configuration), but it will not create a response
+        # from the model. The server will respond with an `input_audio_buffer.committed`
+        # event.
+        variant :"input_audio_buffer.commit", -> { OpenAI::Realtime::InputAudioBufferCommitEvent }
+
+        # Send this event to cancel an in-progress response. The server will respond
+        # with a `response.done` event with a status of `response.status=cancelled`. If
+        # there is no response to cancel, the server will respond with an error.
+        variant :"response.cancel", -> { OpenAI::Realtime::ResponseCancelEvent }
+
+        # This event instructs the server to create a Response, which means triggering
+        # model inference. When in Server VAD mode, the server will create Responses
+        # automatically.
+        #
+        # A Response will include at least one Item, and may have two, in which case
+        # the second will be a function call. These Items will be appended to the
+        # conversation history.
+        #
+        # The server will respond with a `response.created` event, events for Items
+        # and content created, and finally a `response.done` event to indicate the
+        # Response is complete.
+        #
+        # The `response.create` event includes inference configuration like
+        # `instructions`, and `temperature`. These fields will override the Session's
+        # configuration for this Response only.
+        variant :"response.create", -> { OpenAI::Realtime::ResponseCreateEvent }
+
+        # Send this event to update the session’s default configuration.
+        # The client may send this event at any time to update any field,
+        # except for `voice`. However, note that once a session has been
+        # initialized with a particular `model`, it can’t be changed to
+        # another model using `session.update`.
+        #
+        # When the server receives a `session.update`, it will respond
+        # with a `session.updated` event showing the full, effective configuration.
+        # Only the fields that are present are updated. To clear a field like
+        # `instructions`, pass an empty string.
+        variant :"session.update", -> { OpenAI::Realtime::SessionUpdateEvent }
+
+        # Send this event to update a transcription session.
+        variant :"transcription_session.update", -> { OpenAI::Realtime::TranscriptionSessionUpdate }
+
+        # @!method self.variants
+        #   @return [Array(OpenAI::Models::Realtime::ConversationItemCreateEvent, OpenAI::Models::Realtime::ConversationItemDeleteEvent, OpenAI::Models::Realtime::ConversationItemRetrieveEvent, OpenAI::Models::Realtime::ConversationItemTruncateEvent, OpenAI::Models::Realtime::InputAudioBufferAppendEvent, OpenAI::Models::Realtime::InputAudioBufferClearEvent, OpenAI::Models::Realtime::OutputAudioBufferClearEvent, OpenAI::Models::Realtime::InputAudioBufferCommitEvent, OpenAI::Models::Realtime::ResponseCancelEvent, OpenAI::Models::Realtime::ResponseCreateEvent, OpenAI::Models::Realtime::SessionUpdateEvent, OpenAI::Models::Realtime::TranscriptionSessionUpdate)]
+      end
+    end
+  end
+end

data/lib/openai/models/realtime/realtime_client_secret_config.rb

@@ -0,0 +1,64 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeClientSecretConfig < OpenAI::Internal::Type::BaseModel
+        # @!attribute expires_after
+        #   Configuration for the ephemeral token expiration.
+        #
+        #   @return [OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter, nil]
+        optional :expires_after, -> { OpenAI::Realtime::RealtimeClientSecretConfig::ExpiresAfter }
+
+        # @!method initialize(expires_after: nil)
+        #   Some parameter documentations has been truncated, see
+        #   {OpenAI::Models::Realtime::RealtimeClientSecretConfig} for more details.
+        #
+        #   Configuration options for the generated client secret.
+        #
+        #   @param expires_after [OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter] Configuration for the ephemeral token expiration.
+
+        # @see OpenAI::Models::Realtime::RealtimeClientSecretConfig#expires_after
+        class ExpiresAfter < OpenAI::Internal::Type::BaseModel
+          # @!attribute anchor
+          #   The anchor point for the ephemeral token expiration. Only `created_at` is
+          #   currently supported.
+          #
+          #   @return [Symbol, OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter::Anchor]
+          required :anchor, enum: -> { OpenAI::Realtime::RealtimeClientSecretConfig::ExpiresAfter::Anchor }
+
+          # @!attribute seconds
+          #   The number of seconds from the anchor point to the expiration. Select a value
+          #   between `10` and `7200`.
+          #
+          #   @return [Integer, nil]
+          optional :seconds, Integer
+
+          # @!method initialize(anchor:, seconds: nil)
+          #   Some parameter documentations has been truncated, see
+          #   {OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter} for more
+          #   details.
+          #
+          #   Configuration for the ephemeral token expiration.
+          #
+          #   @param anchor [Symbol, OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter::Anchor] The anchor point for the ephemeral token expiration. Only `created_at` is curren
+          #
+          #   @param seconds [Integer] The number of seconds from the anchor point to the expiration. Select a value be
+
+          # The anchor point for the ephemeral token expiration. Only `created_at` is
+          # currently supported.
+          #
+          # @see OpenAI::Models::Realtime::RealtimeClientSecretConfig::ExpiresAfter#anchor
+          module Anchor
+            extend OpenAI::Internal::Type::Enum
+
+            CREATED_AT = :created_at
+
+            # @!method self.values
+            #   @return [Array<Symbol>]
+          end
+        end
+      end
+    end
+  end
+end