openai 0.22.1 → 0.23.0

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

@@ -11,63 +11,12 @@ module OpenAI
 
         discriminator :type
 
-        variant :function, -> { OpenAI::Realtime::RealtimeToolsConfigUnion::Function }
+        variant :function, -> { OpenAI::Realtime::Models }
 
         # Give the model access to additional tools via remote Model Context Protocol
         # (MCP) servers. [Learn more about MCP](https://platform.openai.com/docs/guides/tools-remote-mcp).
         variant :mcp, -> { OpenAI::Realtime::RealtimeToolsConfigUnion::Mcp }
 
-        class Function < OpenAI::Internal::Type::BaseModel
-          # @!attribute description
-          #   The description of the function, including guidance on when and how to call it,
-          #   and guidance about what to tell the user when calling (if anything).
-          #
-          #   @return [String, nil]
-          optional :description, String
-
-          # @!attribute name
-          #   The name of the function.
-          #
-          #   @return [String, nil]
-          optional :name, String
-
-          # @!attribute parameters
-          #   Parameters of the function in JSON Schema.
-          #
-          #   @return [Object, nil]
-          optional :parameters, OpenAI::Internal::Type::Unknown
-
-          # @!attribute type
-          #   The type of the tool, i.e. `function`.
-          #
-          #   @return [Symbol, OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Function::Type, nil]
-          optional :type, enum: -> { OpenAI::Realtime::RealtimeToolsConfigUnion::Function::Type }
-
-          # @!method initialize(description: nil, name: nil, parameters: nil, type: nil)
-          #   Some parameter documentations has been truncated, see
-          #   {OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Function} for more details.
-          #
-          #   @param description [String] The description of the function, including guidance on when and how
-          #
-          #   @param name [String] The name of the function.
-          #
-          #   @param parameters [Object] Parameters of the function in JSON Schema.
-          #
-          #   @param type [Symbol, OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Function::Type] The type of the tool, i.e. `function`.
-
-          # The type of the tool, i.e. `function`.
-          #
-          # @see OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Function#type
-          module Type
-            extend OpenAI::Internal::Type::Enum
-
-            FUNCTION = :function
-
-            # @!method self.values
-            #   @return [Array<Symbol>]
-          end
-        end
-
         class Mcp < OpenAI::Internal::Type::BaseModel
           # @!attribute server_label
           #   A label for this MCP server, used to identify it in tool calls.
@@ -372,7 +321,7 @@ module OpenAI
         end
 
         # @!method self.variants
-        #   @return [Array(OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Function, OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Mcp)]
+        #   @return [Array(OpenAI::Models::Realtime::Models, OpenAI::Models::Realtime::RealtimeToolsConfigUnion::Mcp)]
       end
     end
   end

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

@@ -3,8 +3,9 @@
 module OpenAI
   module Models
     module Realtime
-      # Configuration options for tracing. Set to null to disable tracing. Once tracing
-      # is enabled for a session, the configuration cannot be modified.
+      # Realtime API can write session traces to the
+      # [Traces Dashboard](/logs?api=traces). 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.
@@ -20,21 +21,21 @@ module OpenAI
         class TracingConfiguration < OpenAI::Internal::Type::BaseModel
           # @!attribute group_id
           #   The group id to attach to this trace to enable filtering and grouping in the
-          #   traces dashboard.
+          #   Traces Dashboard.
           #
           #   @return [String, nil]
           optional :group_id, String
 
           # @!attribute metadata
-          #   The arbitrary metadata to attach to this trace to enable filtering in the traces
-          #   dashboard.
+          #   The arbitrary metadata to attach to this trace to enable filtering in the Traces
+          #   Dashboard.
           #
           #   @return [Object, nil]
           optional :metadata, OpenAI::Internal::Type::Unknown
 
           # @!attribute workflow_name
           #   The name of the workflow to attach to this trace. This is used to name the trace
-          #   in the traces dashboard.
+          #   in the Traces Dashboard.
           #
           #   @return [String, nil]
           optional :workflow_name, String

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

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeTranscriptionSessionAudio < OpenAI::Internal::Type::BaseModel
+        # @!attribute input
+        #
+        #   @return [OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput, nil]
+        optional :input, -> { OpenAI::Realtime::RealtimeTranscriptionSessionAudioInput }
+
+        # @!method initialize(input: nil)
+        #   Configuration for input and output audio.
+        #
+        #   @param input [OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput]
+      end
+    end
+  end
+end

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

@@ -0,0 +1,90 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeTranscriptionSessionAudioInput < OpenAI::Internal::Type::BaseModel
+        # @!attribute format_
+        #   The PCM audio format. Only a 24kHz sample rate is supported.
+        #
+        #   @return [OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCM, OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCMU, OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCMA, nil]
+        optional :format_, union: -> { OpenAI::Realtime::RealtimeAudioFormats }, 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::RealtimeTranscriptionSessionAudioInput::NoiseReduction, nil]
+        optional :noise_reduction, -> { OpenAI::Realtime::RealtimeTranscriptionSessionAudioInput::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::AudioTranscription, nil]
+        optional :transcription, -> { OpenAI::Realtime::AudioTranscription }
+
+        # @!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::RealtimeTranscriptionSessionAudioInputTurnDetection, nil]
+        optional :turn_detection, -> { OpenAI::Realtime::RealtimeTranscriptionSessionAudioInputTurnDetection }
+
+        # @!method initialize(format_: nil, noise_reduction: nil, transcription: nil, turn_detection: nil)
+        #   Some parameter documentations has been truncated, see
+        #   {OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput} for more
+        #   details.
+        #
+        #   @param format_ [OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCM, OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCMU, OpenAI::Models::Realtime::RealtimeAudioFormats::AudioPCMA] The PCM audio format. Only a 24kHz sample rate is supported.
+        #
+        #   @param noise_reduction [OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput::NoiseReduction] Configuration for input audio noise reduction. This can be set to `null` to turn
+        #
+        #   @param transcription [OpenAI::Models::Realtime::AudioTranscription] Configuration for input audio transcription, defaults to off and can be set to `
+        #
+        #   @param turn_detection [OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInputTurnDetection] Configuration for turn detection, ether Server VAD or Semantic VAD. This can be
+
+        # @see OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput#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::NoiseReductionType, nil]
+          optional :type, enum: -> { OpenAI::Realtime::NoiseReductionType }
+
+          # @!method initialize(type: nil)
+          #   Some parameter documentations has been truncated, see
+          #   {OpenAI::Models::Realtime::RealtimeTranscriptionSessionAudioInput::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::NoiseReductionType] Type of noise reduction. `near_field` is for close-talking microphones such as h
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,131 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeTranscriptionSessionAudioInputTurnDetection < 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::RealtimeTranscriptionSessionAudioInputTurnDetection::Eagerness, nil]
+        optional :eagerness,
+                 enum: -> { OpenAI::Realtime::RealtimeTranscriptionSessionAudioInputTurnDetection::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::RealtimeTranscriptionSessionAudioInputTurnDetection::Type, nil]
+        optional :type, enum: -> { OpenAI::Realtime::RealtimeTranscriptionSessionAudioInputTurnDetection::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::RealtimeTranscriptionSessionAudioInputTurnDetection}
+        #   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::RealtimeTranscriptionSessionAudioInputTurnDetection::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::RealtimeTranscriptionSessionAudioInputTurnDetection::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::RealtimeTranscriptionSessionAudioInputTurnDetection#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::RealtimeTranscriptionSessionAudioInputTurnDetection#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
+  end
+end

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

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+
+module OpenAI
+  module Models
+    module Realtime
+      class RealtimeTranscriptionSessionClientSecret < OpenAI::Internal::Type::BaseModel
+        # @!attribute expires_at
+        #   Timestamp for when the token expires. Currently, all tokens expire after one
+        #   minute.
+        #
+        #   @return [Integer]
+        required :expires_at, Integer
+
+        # @!attribute value
+        #   Ephemeral key usable in client environments to authenticate connections to the
+        #   Realtime API. Use this in client-side environments rather than a standard API
+        #   token, which should only be used server-side.
+        #
+        #   @return [String]
+        required :value, String
+
+        # @!method initialize(expires_at:, value:)
+        #   Some parameter documentations has been truncated, see
+        #   {OpenAI::Models::Realtime::RealtimeTranscriptionSessionClientSecret} for more
+        #   details.
+        #
+        #   Ephemeral key returned by the API. Only present when the session is created on
+        #   the server via REST API.
+        #
+        #   @param expires_at [Integer] Timestamp for when the token expires. Currently, all tokens expire
+        #
+        #   @param value [String] Ephemeral key usable in client environments to authenticate connections
+      end
+    end
+
+    RealtimeTranscriptionSessionClientSecret = Realtime::RealtimeTranscriptionSessionClientSecret
+  end
+end