{ "openapi": "3.1.0", "info": { "title": "Kalemio Transcription API", "version": "1.0.0", "description": "Asynchronous Arabic transcription with word timestamps, speaker labels, JSON results, and SRT subtitles. Uploads are authenticated with an API key. An OpenAI-compatible endpoint, POST /v1/audio/transcriptions, answers in the same request; point an OpenAI SDK at https://kalemio.app/v1. Prepaid accounts are billed by recorded duration rounded up to the next second; usage-based accounts are billed at US$0.015 per processed audio minute, rounded up to whole minutes with a minimum of 2 minutes (US$0.03) per job.", "termsOfService": "https://kalemio.app/terms/", "contact": { "email": "support@kalemio.app", "url": "https://kalemio.app/support/" } }, "servers": [ { "url": "https://kalemio.app", "description": "Production" } ], "externalDocs": { "description": "Human-readable API documentation", "url": "https://kalemio.app/developers/docs/" }, "tags": [ { "name": "Account", "description": "Inspect the authenticated account's API balance." }, { "name": "Transcriptions", "description": "Submit audio or video and retrieve its transcription." }, { "name": "OpenAI-compatible", "description": "Endpoints shaped after OpenAI's audio transcription API, so the official openai SDKs work with base_url https://kalemio.app/v1 and a Kalemio key. Jobs share the plans, limits and billing of POST /v1/transcriptions." } ], "security": [ { "apiKeyAuth": [] } ], "paths": { "/v1/account": { "get": { "operationId": "getAccount", "summary": "Get account balance", "description": "Returns the account mode and available transcription credit. Values are expressed in seconds. Requires the `usage:read` key permission.", "tags": [ "Account" ], "responses": { "200": { "description": "Account balance", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Account" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "403": { "$ref": "#/components/responses/Forbidden" }, "429": { "$ref": "#/components/responses/RateLimited" }, "503": { "$ref": "#/components/responses/ServiceUnavailable" } } } }, "/v1/transcriptions": { "post": { "operationId": "createTranscription", "summary": "Submit audio or video", "description": "Queues one Arabic audio or video recording for transcription. The request is asynchronous: save the returned job ID and poll it until it is completed or failed. The same Idempotency-Key may be retried for the same file and speaker settings. Requires the `transcriptions:write` key permission.", "tags": [ "Transcriptions" ], "parameters": [ { "$ref": "#/components/parameters/IdempotencyKey" } ], "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/TranscriptionUpload" } } } }, "responses": { "202": { "description": "Transcription accepted", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TranscriptionJob" } } } }, "400": { "$ref": "#/components/responses/BadRequest" }, "401": { "$ref": "#/components/responses/Unauthorized" }, "402": { "description": "Not enough available credit, or the Free plan minutes for this month are used up (code free_quota_exhausted)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Add minutes before submitting this recording." } } } }, "403": { "$ref": "#/components/responses/Forbidden" }, "409": { "description": "The Idempotency-Key was already used for different upload data", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "413": { "description": "Upload exceeds the 20 MiB limit", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "415": { "description": "The request is not multipart form data", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "422": { "$ref": "#/components/responses/UnprocessableEntity" }, "429": { "$ref": "#/components/responses/RateLimited" }, "503": { "$ref": "#/components/responses/ServiceUnavailable" } } } }, "/v1/transcriptions/{id}": { "get": { "operationId": "getTranscription", "summary": "Get transcription status", "description": "Returns the current state and billing details for a transcription created by the authenticated account. Requires the `transcriptions:read` key permission.", "tags": [ "Transcriptions" ], "parameters": [ { "$ref": "#/components/parameters/TranscriptionId" } ], "responses": { "200": { "description": "Transcription status", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TranscriptionJob" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "403": { "$ref": "#/components/responses/Forbidden" }, "404": { "$ref": "#/components/responses/NotFound" }, "429": { "$ref": "#/components/responses/RateLimited" }, "503": { "$ref": "#/components/responses/ServiceUnavailable" } } } }, "/v1/transcriptions/{id}/result": { "get": { "operationId": "getTranscriptionResult", "summary": "Get a JSON transcription result", "description": "Returns the completed transcription with full text, word-level timestamps, and speaker IDs. Results expire 24 hours after submission. Requires the `transcriptions:read` key permission.", "tags": [ "Transcriptions" ], "parameters": [ { "$ref": "#/components/parameters/TranscriptionId" } ], "responses": { "200": { "description": "Completed transcription", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TranscriptionResult" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "403": { "$ref": "#/components/responses/Forbidden" }, "404": { "$ref": "#/components/responses/NotFound" }, "409": { "description": "The transcription is not completed yet", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "The result is not ready." } } } }, "410": { "description": "The result has expired or is no longer available", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "429": { "$ref": "#/components/responses/RateLimited" }, "503": { "$ref": "#/components/responses/ServiceUnavailable" } } } }, "/v1/transcriptions/{id}/srt": { "get": { "operationId": "getTranscriptionSrt", "summary": "Download SRT subtitles", "description": "Returns the completed transcription as an SRT subtitle file. The result expires 24 hours after submission. Requires the `transcriptions:read` key permission.", "tags": [ "Transcriptions" ], "parameters": [ { "$ref": "#/components/parameters/TranscriptionId" } ], "responses": { "200": { "description": "SRT subtitle file", "headers": { "Content-Disposition": { "description": "Suggested filename for the downloaded subtitle file", "schema": { "type": "string" } } }, "content": { "application/x-subrip": { "schema": { "type": "string" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "403": { "$ref": "#/components/responses/Forbidden" }, "404": { "$ref": "#/components/responses/NotFound" }, "409": { "description": "The transcription is not completed yet", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "410": { "description": "The result has expired or is no longer available", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "429": { "$ref": "#/components/responses/RateLimited" }, "503": { "$ref": "#/components/responses/ServiceUnavailable" } } } }, "/v1/audio/transcriptions": { "post": { "operationId": "createOpenAiTranscription", "summary": "Transcribe audio (OpenAI-compatible)", "description": "Transcribes one Arabic recording and returns the result in the same response, in the shape of OpenAI's create-transcription endpoint. The request waits up to 100 seconds; a job still processing then gets 504 with its id, and sending the identical request again waits on the same job without a second charge. Without an Idempotency-Key, an identical upload (same bytes and speakers setting) that is still processing or finished within the hour is reused. Requires the `transcriptions:write` key permission. Unsupported OpenAI options are rejected with 400 rather than ignored.", "tags": [ "OpenAI-compatible" ], "parameters": [ { "$ref": "#/components/parameters/OptionalIdempotencyKey" } ], "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/OpenAiTranscriptionRequest" } } } }, "responses": { "200": { "description": "The transcription, in the requested response_format", "headers": { "X-Kalemio-Transcription-Id": { "description": "The Kalemio job behind this response. Use it with GET /v1/transcriptions/{id}.", "schema": { "type": "string", "pattern": "^tr_[a-f0-9]{32}$" } } }, "content": { "application/json": { "schema": { "oneOf": [ { "$ref": "#/components/schemas/OpenAiTranscription" }, { "$ref": "#/components/schemas/OpenAiTranscriptionVerbose" }, { "$ref": "#/components/schemas/OpenAiTranscriptionDiarized" } ] } }, "text/plain": { "schema": { "type": "string", "description": "response_format text, srt or vtt." } }, "text/event-stream": { "schema": { "type": "string", "description": "stream=true: transcript.text.delta events (and transcript.text.segment events for diarized_json), then transcript.text.done. Sent once the recording is transcribed, not progressively." } } } }, "400": { "description": "Invalid or unsupported parameter, or unreadable media (code, for example, unsupported_language, unsupported_parameter, invalid_file_format, audio_too_long)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "401": { "description": "The API key is missing, invalid or revoked (code invalid_api_key)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "403": { "description": "The API key lacks the transcriptions:write permission", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "404": { "description": "model is not a Kalemio model id (code model_not_found). OpenAI model names are not accepted.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "409": { "description": "The Idempotency-Key belongs to a different upload", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "410": { "description": "The result of the reused job has expired", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "413": { "description": "The file exceeds 20 MiB (code file_too_large)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "415": { "description": "The request is not multipart form data", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "429": { "description": "Rate limited (rate_limit_exceeded, or a free_* code), or out of minutes (insufficient_quota, sent with x-should-retry: false)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } }, "headers": { "Retry-After": { "description": "Seconds until the rate-limit window resets, when supplied", "schema": { "type": "integer", "minimum": 0 } } } }, "500": { "description": "The transcription failed (code transcription_failed). Reserved prepaid minutes are returned.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "503": { "description": "The API is temporarily unavailable", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "504": { "description": "Still processing at the deadline (code transcription_pending). error.transcription_id names the job.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } }, "headers": { "X-Kalemio-Transcription-Id": { "description": "The Kalemio job behind this response. Use it with GET /v1/transcriptions/{id}.", "schema": { "type": "string", "pattern": "^tr_[a-f0-9]{32}$" } }, "Retry-After": { "description": "Seconds to wait before sending the same request again", "schema": { "type": "integer", "minimum": 0 } } } } } } }, "/v1/models": { "get": { "operationId": "listModels", "summary": "List models (OpenAI-compatible)", "description": "Lists the model ids POST /v1/audio/transcriptions accepts. No key is needed; a key that is sent must be valid.", "tags": [ "OpenAI-compatible" ], "security": [ {}, { "apiKeyAuth": [] } ], "responses": { "200": { "description": "Model list", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ModelList" } } } }, "401": { "description": "A key was sent and it is invalid or revoked", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } } } } }, "/v1/models/{model}": { "get": { "operationId": "retrieveModel", "summary": "Retrieve a model (OpenAI-compatible)", "tags": [ "OpenAI-compatible" ], "security": [ {}, { "apiKeyAuth": [] } ], "parameters": [ { "name": "model", "in": "path", "required": true, "schema": { "type": "string" }, "example": "kalemio-arabic-1" } ], "responses": { "200": { "description": "The model", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Model" } } } }, "401": { "description": "A key was sent and it is invalid or revoked", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } }, "404": { "description": "No such model (code model_not_found)", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/OpenAIError" } } } } } } } }, "components": { "securitySchemes": { "apiKeyAuth": { "type": "http", "scheme": "bearer", "bearerFormat": "kal_live_<64 hex characters>", "description": "Create a scoped key in your Kalemio account, then send it as `Authorization: Bearer kal_live_...`. Keep keys on your server. Rotate lost or exposed keys; the prior key is revoked immediately." } }, "parameters": { "IdempotencyKey": { "name": "Idempotency-Key", "in": "header", "required": true, "description": "A stable identifier for this upload attempt. Use 8–128 letters, digits, dots, colons, underscores, or hyphens. Reuse it only for the same file and speaker settings.", "schema": { "type": "string", "minLength": 8, "maxLength": 128, "pattern": "^[A-Za-z0-9_.:-]+$" }, "example": "recording-2026-001" }, "TranscriptionId": { "name": "id", "in": "path", "required": true, "description": "The transcription job ID returned by the upload request.", "schema": { "type": "string", "pattern": "^tr_[a-f0-9]{32}$" }, "example": "tr_0123456789abcdef0123456789abcdef" }, "OptionalIdempotencyKey": { "name": "Idempotency-Key", "in": "header", "required": false, "description": "Optional here. The same key with the same file and speakers setting returns the same job without a second charge. 8–128 letters, digits, dots, colons, underscores, or hyphens.", "schema": { "type": "string", "minLength": 8, "maxLength": 128, "pattern": "^[A-Za-z0-9_.:-]+$" } } }, "responses": { "BadRequest": { "description": "The request is invalid", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "Unauthorized": { "description": "The API key is missing, invalid, or revoked", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "A valid API key is required." } } } }, "Forbidden": { "description": "The API key does not have the permission required by this operation", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "NotFound": { "description": "The transcription does not exist for this account", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "RateLimited": { "description": "Too many requests. Retry after a short delay.", "headers": { "Retry-After": { "description": "Number of seconds to wait before retrying, when supplied", "schema": { "type": "integer", "minimum": 0 } } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "ServiceUnavailable": { "description": "The API is temporarily unavailable or transcription has not launched", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "UnprocessableEntity": { "description": "The media or form fields are invalid", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" }, "example": { "error": "Language must be ar; speakers must be auto or 1–20." } } } } }, "schemas": { "Error": { "type": "object", "required": [ "error" ], "properties": { "error": { "type": "string", "description": "Human-readable error message." }, "code": { "type": "string", "description": "Machine-readable reason, when one applies: free_quota_exhausted (402), invalid_file_format or audio_too_long (422), free_concurrency_limit, free_rate_limited or free_queue_full (429)." } }, "additionalProperties": false }, "Account": { "type": "object", "required": [ "mode", "available_seconds", "monthly_seconds", "topup_seconds", "billing_method", "metered_price_usd_per_minute", "transcription_enabled", "processing", "free_plan" ], "properties": { "mode": { "type": "string", "enum": [ "live", "test" ] }, "available_seconds": { "type": "integer", "description": "Total credit currently available, in seconds." }, "monthly_seconds": { "type": "integer", "description": "Available seconds from the current monthly allowance." }, "topup_seconds": { "type": "integer", "description": "Available seconds from non-expiring top-ups." }, "billing_method": { "type": "string", "enum": [ "credits", "metered_api_v1", "free" ], "description": "The billing path used by new transcription jobs." }, "metered_price_usd_per_minute": { "type": [ "number", "null" ], "description": "The usage-based price in US dollars per processed minute, as Stripe charges it, when billing_method is metered_api_v1." }, "transcription_enabled": { "type": "boolean", "description": "Whether the transcription backend is currently enabled." }, "processing": { "type": "string", "enum": [ "standard", "priority" ], "description": "standard: Free plan jobs, which use slower, queued processing on a best-effort basis and are typically several times slower than paid plans. priority: paid plans, with priority, faster processing." }, "free_plan": { "anyOf": [ { "type": "object", "required": [ "minutes_included", "minutes_used", "minutes_remaining", "resets_at", "processing" ], "properties": { "minutes_included": { "type": "integer", "description": "Free minutes per calendar month (UTC)." }, "minutes_used": { "type": "integer", "description": "Whole minutes counted this month, rounded up per job with a minimum of one." }, "minutes_remaining": { "type": "integer" }, "resets_at": { "type": "string", "format": "date-time" }, "processing": { "type": "string", "const": "standard" } }, "additionalProperties": false }, { "type": "null" } ], "description": "The Free plan allowance this month, or null on a paid plan." } }, "additionalProperties": false }, "TranscriptionUpload": { "type": "object", "required": [ "file" ], "properties": { "file": { "type": "string", "format": "binary", "description": "One MP3, M4A, PCM WAV, MP4, or MOV file, up to 20 MiB and 10 minutes." }, "language": { "type": "string", "enum": [ "ar" ], "default": "ar", "description": "The recording language. Arabic is currently supported." }, "speakers": { "type": "string", "pattern": "^(auto|[1-9]|1[0-9]|20)$", "default": "auto", "description": "Use automatic speaker detection, or provide a known speaker count from 1 to 20." } }, "additionalProperties": false }, "TranscriptionJob": { "type": "object", "required": [ "id", "status", "duration_seconds", "billed_seconds", "billed_minutes", "reserved_seconds", "billing_method", "expires_at", "processing" ], "properties": { "id": { "type": "string", "pattern": "^tr_[a-f0-9]{32}$" }, "status": { "type": "string", "enum": [ "queued", "running", "completed", "failed" ] }, "duration_seconds": { "type": "number", "exclusiveMinimum": 0, "description": "Measured media duration before billing rounding." }, "billed_seconds": { "type": "integer", "minimum": 0, "description": "Seconds charged after a successful transcription for prepaid credit accounts; zero for metered accounts." }, "billed_minutes": { "type": "integer", "minimum": 0, "description": "Whole minutes counted after a successful transcription for usage-based and Free plan jobs, rounded up. Usage-based jobs are billed for at least 2 minutes; Free plan jobs count at least one minute." }, "reserved_seconds": { "type": "integer", "minimum": 0, "description": "Prepaid seconds reserved while the job is active; zero for metered accounts." }, "billing_method": { "type": "string", "enum": [ "credits", "metered_api_v1", "free" ], "description": "The billing path used for this job." }, "error": { "type": "string", "description": "Present when status is failed. Failed jobs return reserved credit." }, "expires_at": { "type": "string", "format": "date-time", "description": "Result retention deadline." }, "processing": { "type": "string", "enum": [ "standard", "priority" ], "description": "standard: Free plan jobs, which use slower, queued processing on a best-effort basis and are typically several times slower than paid plans. priority: paid plans, with priority, faster processing." } }, "additionalProperties": false }, "Word": { "type": "object", "required": [ "text", "start", "end", "speaker_id" ], "properties": { "text": { "type": "string" }, "start": { "type": "number", "minimum": 0, "description": "Word start time in seconds." }, "end": { "type": "number", "minimum": 0, "description": "Word end time in seconds." }, "speaker_id": { "type": [ "string", "null" ], "description": "Speaker label within this recording, or null when unavailable." } }, "additionalProperties": false }, "TranscriptionResult": { "type": "object", "required": [ "text", "words", "duration_seconds" ], "properties": { "text": { "type": "string", "description": "The complete transcript assembled from the word results." }, "words": { "type": "array", "items": { "$ref": "#/components/schemas/Word" } }, "duration_seconds": { "type": "number", "minimum": 0 } }, "additionalProperties": false }, "OpenAIError": { "type": "object", "required": [ "error" ], "properties": { "error": { "type": "object", "required": [ "message", "type", "param", "code" ], "properties": { "message": { "type": "string" }, "type": { "type": "string", "description": "invalid_request_error, insufficient_quota, requests or server_error." }, "param": { "type": [ "string", "null" ] }, "code": { "type": [ "string", "null" ] }, "transcription_id": { "type": "string", "description": "Present on transcription_pending and transcription_failed." } } } } }, "OpenAiTranscriptionRequest": { "type": "object", "required": [ "file", "model" ], "properties": { "file": { "type": "string", "format": "binary", "description": "One MP3, M4A, PCM WAV, MP4, or MOV file, up to 20 MiB and 10 minutes. FLAC, OGG and WebM are not accepted." }, "model": { "type": "string", "enum": [ "kalemio-arabic-1" ] }, "language": { "type": "string", "enum": [ "ar" ], "description": "Optional. Arabic only; dialects need no separate hint." }, "response_format": { "type": "string", "enum": [ "json", "text", "srt", "vtt", "verbose_json", "diarized_json" ], "default": "json" }, "timestamp_granularities[]": { "type": "array", "items": { "type": "string", "enum": [ "word", "segment" ] }, "description": "verbose_json only. Defaults to segment." }, "stream": { "type": "boolean", "default": false, "description": "With json, text or diarized_json. Events are sent once the recording is transcribed." }, "temperature": { "type": "number", "enum": [ 0 ], "description": "Only 0 (the default) is accepted." }, "chunking_strategy": { "type": "string", "enum": [ "auto" ] }, "speakers": { "type": "string", "pattern": "^(auto|[1-9]|1[0-9]|20)$", "default": "auto", "description": "Kalemio extension: automatic speaker detection or a known count from 1 to 20." } }, "description": "prompt (when not empty), keywords[], include[], known_speaker_names[], known_speaker_references[], non-Arabic language values, other chunking strategies and unknown fields are rejected with 400." }, "OpenAiTranscription": { "type": "object", "required": [ "text", "usage" ], "properties": { "text": { "type": "string" }, "usage": { "type": "object", "required": [ "type", "seconds" ], "properties": { "type": { "type": "string", "const": "duration" }, "seconds": { "type": "integer", "description": "Recording duration in seconds, rounded up." } } } } }, "OpenAiWord": { "type": "object", "required": [ "word", "start", "end" ], "properties": { "word": { "type": "string" }, "start": { "type": "number" }, "end": { "type": "number" } } }, "OpenAiSegment": { "type": "object", "required": [ "id", "seek", "start", "end", "text", "tokens", "temperature", "avg_logprob", "compression_ratio", "no_speech_prob" ], "description": "seek, tokens, temperature, avg_logprob, compression_ratio and no_speech_prob are fixed placeholders (0 or []) kept for schema compatibility; Kalemio does not compute them.", "properties": { "id": { "type": "integer" }, "seek": { "type": "integer" }, "start": { "type": "number" }, "end": { "type": "number" }, "text": { "type": "string" }, "tokens": { "type": "array", "items": { "type": "integer" } }, "temperature": { "type": "number" }, "avg_logprob": { "type": "number" }, "compression_ratio": { "type": "number" }, "no_speech_prob": { "type": "number" } } }, "OpenAiTranscriptionVerbose": { "type": "object", "required": [ "task", "language", "duration", "text", "usage" ], "properties": { "task": { "type": "string", "const": "transcribe" }, "language": { "type": "string", "const": "arabic" }, "duration": { "type": "number" }, "text": { "type": "string" }, "segments": { "type": "array", "items": { "$ref": "#/components/schemas/OpenAiSegment" } }, "words": { "type": "array", "items": { "$ref": "#/components/schemas/OpenAiWord" } }, "usage": { "type": "object", "required": [ "type", "seconds" ], "properties": { "type": { "type": "string", "const": "duration" }, "seconds": { "type": "integer", "description": "Recording duration in seconds, rounded up." } } } } }, "OpenAiDiarizedSegment": { "type": "object", "required": [ "type", "id", "start", "end", "text", "speaker" ], "properties": { "type": { "type": "string", "const": "transcript.text.segment" }, "id": { "type": "string" }, "start": { "type": "number" }, "end": { "type": "number" }, "text": { "type": "string" }, "speaker": { "type": "string", "description": "A, B, C… in order of first appearance within this recording." } } }, "OpenAiTranscriptionDiarized": { "type": "object", "required": [ "task", "duration", "text", "segments", "usage" ], "properties": { "task": { "type": "string", "const": "transcribe" }, "duration": { "type": "number" }, "text": { "type": "string" }, "segments": { "type": "array", "items": { "$ref": "#/components/schemas/OpenAiDiarizedSegment" } }, "usage": { "type": "object", "required": [ "type", "seconds" ], "properties": { "type": { "type": "string", "const": "duration" }, "seconds": { "type": "integer", "description": "Recording duration in seconds, rounded up." } } } } }, "Model": { "type": "object", "required": [ "id", "object", "created", "owned_by" ], "properties": { "id": { "type": "string" }, "object": { "type": "string", "const": "model" }, "created": { "type": "integer" }, "owned_by": { "type": "string" } } }, "ModelList": { "type": "object", "required": [ "object", "data" ], "properties": { "object": { "type": "string", "const": "list" }, "data": { "type": "array", "items": { "$ref": "#/components/schemas/Model" } } } } } } }