Changes to Create session

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #2: Input text]/prompt_cache_breakpoint/ttl

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #3: Input image]/prompt_cache_breakpoint/ttl

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #4: Input file]/prompt_cache_breakpoint/ttl

the response property audio/input/noise_reduction became nullable for the status 200

the response property audio/input/transcription/language became nullable for the status 200

the response property audio/input/turn_detection became nullable for the status 200

the response property turn_detection became nullable for the status 200

the modalities request property type changed from no type to array

added the new gpt-live-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the new gpt-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #2: Input text]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #3: Input image]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #4: Input file]/prompt_cache_breakpoint

added the new auto enum value to the request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #4: Input file]/detail

added the optional property audio/input/transcription/languages to the response with the 200 status

added the new gpt-live-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the new gpt-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the optional property audio/input/transcription/keywords to the response with the 200 status

added the optional property audio/input/transcription/languages to the response with the 200 status

added the new gpt-live-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the new gpt-transcribe enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the optional property audio/input/transcription/languages to the response with the 200 status

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #2: Input text]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #3: Input image]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #4: Input file]/prompt_cache_breakpoint

added the new auto enum value to the request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/oneOf[subschema #4: Input file]/detail

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #2: Input text]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #3: Input image]/prompt_cache_breakpoint

added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/prompt_cache_breakpoint

added the new auto enum value to the request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/detail

added the new required request property client_secret

removed subschema #1 subschema #2 from the voice request property anyOf list

removed the enum value g711_alaw of the request property input_audio_format

removed the enum value g711_alaw of the request property output_audio_format

removed the enum value g711_ulaw of the request property input_audio_format

removed the enum value g711_ulaw of the request property output_audio_format

removed the enum value pcm16 of the request property input_audio_format

removed the enum value pcm16 of the request property output_audio_format

removed the enum value semantic_vad of the request property turn_detection/type

removed the enum value server_vad of the request property turn_detection/type

removed the required property client_secret from the response with the 200 status

removed the request property input_audio_noise_reduction

removed the request property input_audio_transcription/language

removed the request property input_audio_transcription/prompt

removed the request property model

removed the request property turn_detection/create_response

removed the request property turn_detection/eagerness

removed the request property turn_detection/interrupt_response

removed the optional property input_audio_format from the response with the 200 status

removed the optional property input_audio_transcription from the response with the 200 status

removed the optional property max_response_output_tokens from the response with the 200 status

removed the optional property modalities from the response with the 200 status

removed the optional property output_audio_format from the response with the 200 status

removed the optional property temperature from the response with the 200 status

removed the optional property voice from the response with the 200 status

added the new optional request property prompt

added the new optional request property speed

added the new optional request property tracing

added the new optional request property truncation

added VoiceIdsShared subschema #2 to the voice request property anyOf list

the request property default value text audio was removed

the input_audio_format request property default value pcm16 was removed

the output_audio_format request property default value pcm16 was removed

the temperature request property default value 0.8 was removed

the tool_choice request property default value auto was removed

the type request property default value server_vad was removed

added the optional property audio to the response with the 200 status

added the optional property expires_at to the response with the 200 status

added the optional property id to the response with the 200 status

added the optional property include to the response with the 200 status

added the optional property max_output_tokens to the response with the 200 status

added the optional property model to the response with the 200 status

added the optional property object to the response with the 200 status

added the optional property output_modalities to the response with the 200 status

added the optional property tracing to the response with the 200 status

added the new gpt-realtime-whisper enum value to the audio/input/transcription/model/anyOf[subschema #2] response property for the response status 200

added the optional property audio/input/transcription/delay to the response with the 200 status

the prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #3: Input image]/image_url/anyOf[subschema #1] request property format changed from no format to uri

the prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/file_url request property format changed from no format to uri

the client_secret/expires_at request property format changed from no format to unixtime

added the new required request property client_secret

removed subschema #1 subschema #2 from the voice request property anyOf list

removed the enum value g711_alaw of the request property input_audio_format

removed the enum value g711_alaw of the request property output_audio_format

removed the enum value g711_ulaw of the request property input_audio_format

removed the enum value g711_ulaw of the request property output_audio_format

removed the enum value pcm16 of the request property input_audio_format

removed the enum value pcm16 of the request property output_audio_format

removed the enum value semantic_vad of the request property turn_detection/type

removed the enum value server_vad of the request property turn_detection/type

removed subschema #1 subschema #2 from the max_response_output_tokens request property oneOf list

removed the required property client_secret from the response with the 200 status

removed the request property input_audio_noise_reduction

removed the request property input_audio_transcription/language

removed the request property input_audio_transcription/prompt

removed the request property model

removed the request property turn_detection/create_response

removed the request property turn_detection/eagerness

removed the request property turn_detection/interrupt_response

removed the optional property input_audio_format from the response with the 200 status

removed the optional property input_audio_transcription from the response with the 200 status

removed the optional property max_response_output_tokens from the response with the 200 status

removed the optional property modalities from the response with the 200 status

removed the optional property output_audio_format from the response with the 200 status

removed the optional property temperature from the response with the 200 status

removed the optional property voice from the response with the 200 status

added the new optional request property prompt

added the new optional request property speed

added the new optional request property tracing

added the new optional request property truncation

added VoiceIdsShared subschema #2 to the voice request property anyOf list

added subschema #1 subschema #2 to the max_response_output_tokens request property anyOf list

the request property default value text audio was removed

the input_audio_format request property default value pcm16 was removed

the output_audio_format request property default value pcm16 was removed

the temperature request property default value 0.8 was removed

the tool_choice request property default value auto was removed

the type request property default value server_vad was removed

added the optional property audio to the response with the 200 status

added the optional property expires_at to the response with the 200 status

added the optional property id to the response with the 200 status

added the optional property include to the response with the 200 status

added the optional property max_output_tokens to the response with the 200 status

added the optional property model to the response with the 200 status

added the optional property object to the response with the 200 status

added the optional property output_modalities to the response with the 200 status

added the optional property tracing to the response with the 200 status

request property turn_detection/type was restricted to a list of enum values

removed the enum value alloy of the request property voice

removed the enum value ash of the request property voice

removed the enum value ballad of the request property voice

removed the enum value coral of the request property voice

removed the enum value echo of the request property voice

removed the enum value sage of the request property voice

removed the enum value shimmer of the request property voice

removed the enum value verse of the request property voice

the voice request property type changed from string to no type

the voice response's property type changed from string to no type for status 200

added the new optional request property input_audio_noise_reduction

added the new optional request property turn_detection/eagerness

added subschema #1 subschema #2 to the voice request property anyOf list

the request property default value text audio was added

the input_audio_format request property default value pcm16 was added

the output_audio_format request property default value pcm16 was added

the temperature request property default value 0.8 was added

the tool_choice request property default value auto was added

the type request property default value server_vad was added

added the new semantic_vad enum value to the request property turn_detection/type

added the new server_vad enum value to the request property turn_detection/type

added subschema #1 subschema #2 to the voice response property anyOf list for the response status 200

removed the alloy enum value from the voice response property for the response status 200

removed the ash enum value from the voice response property for the response status 200

removed the ballad enum value from the voice response property for the response status 200

removed the coral enum value from the voice response property for the response status 200

removed the echo enum value from the voice response property for the response status 200

removed the sage enum value from the voice response property for the response status 200

removed the shimmer enum value from the voice response property for the response status 200

removed the verse enum value from the voice response property for the response status 200

added the new optional request property turn_detection/interrupt_response

added the new optional request property input_audio_transcription/language

added the new optional request property input_audio_transcription/prompt

the response property client_secret became required for the status 200

the response property client_secret/expires_at became required for the status 200

the response property client_secret/value became required for the status 200

the request property model became optional

the request property model became required

the request property model became optional

endpoint added