GET
/v1/schemas/openai/audio/audio%2Ftranscriptions?kind=output
Accept:
Response body
0 properties · 0 required · 0 $defsThis schema isn’t a plain object with properties — showing the raw JSON instead.
application/json
{
"provider": "openai",
"activity": "audio",
"endpointId": "audio/transcriptions",
"kind": "output",
"contentHash": "e83d8f8c016ca384a0e09125b7b9c2446311ed6288d14da2cb2fc7dc334711a0",
"specRevision": "67e2bc61160adba75bdd81dc17e48f649b82e4e97eddf128a40367c4fc7413bc",
"provenance": {
"sourceUrl": "https://raw.githubusercontent.com/openai/openai-node/main/api_reference/openapi.transformed.yml",
"sourceHash": "67e2bc61160adba75bdd81dc17e48f649b82e4e97eddf128a40367c4fc7413bc",
"fetchedAt": 1790658647,
"extractorVersion": "1",
"derivation": "upstream-spec",
"verifiedAt": null
},
"createdAt": 1790658647,
"supersededAt": null,
"schema": {
"anyOf": [
{
"$ref": "#/$defs/CreateTranscriptionResponseJson"
},
{
"$ref": "#/$defs/CreateTranscriptionResponseDiarizedJson",
"x-stainless-skip": [
"go"
]
},
{
"$ref": "#/$defs/CreateTranscriptionResponseVerboseJson"
}
],
"discriminator": {
"propertyName": "task"
},
"$defs": {
"CreateTranscriptionResponseDiarizedJson": {
"type": "object",
"description": "Represents a diarized transcription response returned by the model, including the combined transcript and speaker-segment annotations.\n",
"properties": {
"task": {
"type": "string",
"description": "The type of task that was run. Always `transcribe`.",
"enum": [
"transcribe"
],
"x-stainless-const": true
},
"duration": {
"type": "number",
"format": "double",
"description": "Duration of the input audio in seconds."
},
"text": {
"type": "string",
"description": "The concatenated transcript text for the entire audio input."
},
"segments": {
"type": "array",
"description": "Segments of the transcript annotated with timestamps and speaker labels.",
"items": {
"$ref": "#/$defs/TranscriptionDiarizedSegment"
}
},
"usage": {
"type": "object",
"description": "Token or duration usage statistics for the request.",
"discriminator": {
"propertyName": "type"
},
"anyOf": [
{
"$ref": "#/$defs/TranscriptTextUsageTokens",
"title": "Token Usage"
},
{
"$ref": "#/$defs/TranscriptTextUsageDuration",
"title": "Duration Usage"
}
]
}
},
"required": [
"task",
"duration",
"text",
"segments"
],
"x-oaiMeta": {
"name": "The transcription object (Diarized JSON)",
"group": "audio",
"example": "{\n \"task\": \"transcribe\",\n \"duration\": 42.7,\n \"text\": \"Agent: Thanks for calling OpenAI support.\\nCustomer: Hi, I need help with diarization.\",\n \"segments\": [\n {\n \"type\": \"transcript.text.segment\",\n \"id\": \"seg_001\",\n \"start\": 0.0,\n \"end\": 5.2,\n \"text\": \"Thanks for calling OpenAI support.\",\n \"speaker\": \"agent\"\n },\n {\n \"type\": \"transcript.text.segment\",\n \"id\": \"seg_002\",\n \"start\": 5.2,\n \"end\": 12.8,\n \"text\": \"Hi, I need help with diarization.\",\n \"speaker\": \"A\"\n }\n ],\n \"usage\": {\n \"type\": \"duration\",\n \"seconds\": 43\n }\n}\n"
}
},
"CreateTranscriptionResponseJson": {
"type": "object",
"description": "Represents a transcription response returned by model, based on the provided input.",
"properties": {
"text": {
"type": "string",
"description": "The transcribed text."
},
"languages": {
"type": "array",
"description": "The languages detected in the audio. Returned by `gpt-transcribe`. An empty array indicates that no language could be reliably detected.\n",
"items": {
"$ref": "#/$defs/TranscriptionLanguage"
}
},
"logprobs": {
"type": "array",
"optional": true,
"description": "The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array.\n",
"items": {
"type": "object",
"properties": {
"token": {
"type": "string",
"description": "The token in the transcription."
},
"logprob": {
"type": "number",
"description": "The log probability of the token."
},
"bytes": {
"type": "array",
"items": {
"type": "number"
},
"description": "The bytes of the token."
}
}
}
},
"usage": {
"type": "object",
"description": "Token usage statistics for the request.",
"anyOf": [
{
"$ref": "#/$defs/TranscriptTextUsageTokens",
"title": "Token Usage"
},
{
"$ref": "#/$defs/TranscriptTextUsageDuration",
"title": "Duration Usage"
}
],
"discriminator": {
"propertyName": "type"
}
}
},
"required": [
"text"
],
"x-oaiMeta": {
"name": "The transcription object (JSON)",
"group": "audio",
"example": "{\n \"text\": \"Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that.\",\n \"usage\": {\n \"type\": \"tokens\",\n \"input_tokens\": 14,\n \"input_token_details\": {\n \"text_tokens\": 10,\n \"audio_tokens\": 4\n },\n \"output_tokens\": 101,\n \"total_tokens\": 115\n }\n}\n"
}
},
"CreateTranscriptionResponseVerboseJson": {
"type": "object",
"description": "Represents a verbose json transcription response returned by model, based on the provided input.",
"properties": {
"language": {
"type": "string",
"description": "The language of the input audio."
},
"duration": {
"type": "number",
"format": "double",
"description": "The duration of the input audio."
},
"text": {
"type": "string",
"description": "The transcribed text."
},
"words": {
"type": "array",
"description": "Extracted words and their corresponding timestamps.",
"items": {
"$ref": "#/$defs/TranscriptionWord"
}
},
"segments": {
"type": "array",
"description": "Segments of the transcribed text and their corresponding details.",
"items": {
"$ref": "#/$defs/TranscriptionSegment"
}
},
"usage": {
"$ref": "#/$defs/TranscriptTextUsageDuration"
}
},
"required": [
"language",
"duration",
"text"
],
"x-oaiMeta": {
"name": "The transcription object (Verbose JSON)",
"group": "audio",
"example": "{\n \"task\": \"transcribe\",\n \"language\": \"english\",\n \"duration\": 3.32,\n \"text\": \"The beach was a popular spot on a hot summer day.\",\n \"segments\": [\n {\n \"id\": 0,\n \"seek\": 0,\n \"start\": 0.0,\n \"end\": 3.319999933242798,\n \"text\": \" The beach was a popular spot on a hot summer day.\",\n \"tokens\": [\n 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530\n ],\n \"temperature\": 0.0,\n \"avg_logprob\": -0.2860786020755768,\n \"compression_ratio\": 1.2363636493682861,\n \"no_speech_prob\": 0.00985979475080967\n }\n ],\n \"usage\": {\n \"type\": \"duration\",\n \"seconds\": 4\n }\n}\n"
}
},
"TranscriptTextUsageDuration": {
"type": "object",
"title": "TranscriptTextUsageDuration",
"description": "Usage statistics for models billed by audio input duration.",
"properties": {
"type": {
"type": "string",
"enum": [
"duration"
],
"description": "The type of the usage object. Always `duration` for this variant.",
"x-stainless-const": true
},
"seconds": {
"type": "number",
"format": "double",
"description": "Duration of the input audio in seconds."
}
},
"required": [
"type",
"seconds"
]
},
"TranscriptTextUsageTokens": {
"type": "object",
"title": "TranscriptTextUsageTokens",
"description": "Usage statistics for models billed by token usage.",
"properties": {
"type": {
"type": "string",
"enum": [
"tokens"
],
"description": "The type of the usage object. Always `tokens` for this variant.",
"x-stainless-const": true
},
"input_tokens": {
"type": "integer",
"description": "Number of input tokens billed for this request."
},
"input_token_details": {
"type": "object",
"description": "Details about the input tokens billed for this request.",
"properties": {
"text_tokens": {
"type": "integer",
"description": "Number of text tokens billed for this request."
},
"audio_tokens": {
"type": "integer",
"description": "Number of audio tokens billed for this request."
}
}
},
"output_tokens": {
"type": "integer",
"description": "Number of output tokens generated."
},
"total_tokens": {
"type": "integer",
"description": "Total number of tokens used (input + output)."
}
},
"required": [
"type",
"input_tokens",
"output_tokens",
"total_tokens"
]
},
"TranscriptionDiarizedSegment": {
"type": "object",
"description": "A segment of diarized transcript text with speaker metadata.",
"properties": {
"type": {
"type": "string",
"description": "The type of the segment. Always `transcript.text.segment`.\n",
"enum": [
"transcript.text.segment"
],
"x-stainless-const": true
},
"id": {
"type": "string",
"description": "Unique identifier for the segment."
},
"start": {
"type": "number",
"format": "double",
"description": "Start timestamp of the segment in seconds."
},
"end": {
"type": "number",
"format": "double",
"description": "End timestamp of the segment in seconds."
},
"text": {
"type": "string",
"description": "Transcript text for this segment."
},
"speaker": {
"type": "string",
"description": "Speaker label for this segment. When known speakers are provided, the label matches `known_speaker_names[]`. Otherwise speakers are labeled sequentially using capital letters (`A`, `B`, ...).\n"
}
},
"required": [
"type",
"id",
"start",
"end",
"text",
"speaker"
]
},
"TranscriptionLanguage": {
"type": "object",
"description": "A language detected in transcribed audio.",
"properties": {
"code": {
"type": "string",
"description": "The code of a language detected in the audio."
}
},
"required": [
"code"
]
},
"TranscriptionSegment": {
"type": "object",
"properties": {
"id": {
"type": "integer",
"description": "Unique identifier of the segment."
},
"seek": {
"type": "integer",
"description": "Seek offset of the segment."
},
"start": {
"type": "number",
"format": "double",
"description": "Start time of the segment in seconds."
},
"end": {
"type": "number",
"format": "double",
"description": "End time of the segment in seconds."
},
"text": {
"type": "string",
"description": "Text content of the segment."
},
"tokens": {
"type": "array",
"items": {
"type": "integer"
},
"description": "Array of token IDs for the text content."
},
"temperature": {
"type": "number",
"format": "float",
"description": "Temperature parameter used for generating the segment."
},
"avg_logprob": {
"type": "number",
"format": "float",
"description": "Average logprob of the segment. If the value is lower than -1, consider the logprobs failed."
},
"compression_ratio": {
"type": "number",
"format": "float",
"description": "Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed."
},
"no_speech_prob": {
"type": "number",
"format": "float",
"description": "Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent."
}
},
"required": [
"id",
"seek",
"start",
"end",
"text",
"tokens",
"temperature",
"avg_logprob",
"compression_ratio",
"no_speech_prob"
]
},
"TranscriptionWord": {
"type": "object",
"properties": {
"word": {
"type": "string",
"description": "The text content of the word."
},
"start": {
"type": "number",
"format": "double",
"description": "Start time of the word in seconds."
},
"end": {
"type": "number",
"format": "double",
"description": "End time of the word in seconds."
}
},
"required": [
"word",
"start",
"end"
]
}
}
}
}Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"openai","endpointId":"audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}