vCita AI Audio Transcriptions API
Transcribe audio files using multiple providers
Transcribe audio files using multiple providers
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/vcita:vcita-ai-audio-transcriptions-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: AI Audio Transcriptions API
description: Unified OpenAPI specification for ai domain
version: '3.0'
x-generated:
sourceFiles:
- recommendations.json
- business_rules.json
- business_ai_settings.json
- bizai.json
- ai_smart_reply.json
- generic_ai.json
- staff_ai_settings.json
- ai_generation_feedback.json
pathNormalizations: []
pathConflicts: []
componentConflicts:
- type: schema
name: ErrorResponse
resolution: Renamed to ErrorResponse_business_rules
files:
- merged
- business_rules.json
- type: schema
name: ErrorResponse
resolution: Renamed to ErrorResponse_business_ai_settings
files:
- merged
- business_ai_settings.json
- type: schema
name: Response
resolution: Renamed to Response_ai_smart_reply
files:
- merged
- ai_smart_reply.json
- type: schema
name: ErrorResponse
resolution: Renamed to ErrorResponse_staff_ai_settings
files:
- merged
- staff_ai_settings.json
totalPaths: 20
totalComponents: 33
servers:
- url: https://api.vcita.biz
description: Unified API Gateway server
tags:
- name: AI Audio Transcriptions
description: Transcribe audio files using multiple providers
paths:
/v3/ai/audio_transcriptions:
post:
tags:
- AI Audio Transcriptions
summary: Create an AudioTranscription
description: '## Overview
Transcribe audio files using multiple providers (OpenAI Whisper, OpenAI GPT-4o Transcribe, Google Chirp). Supports file upload via multipart form data.
### Supported Models
| Provider | Models |
|----------|--------|
| OpenAI | `openai/whisper-1`, `openai/gpt-4o-transcribe` |
| Google | `google/chirp-2` |
### Async Mode
Set `async: true` to queue the transcription and receive a run UID. Poll `GET /v3/ai/transcription_runs/{uid}` for the result. Recommended for long audio files or diarization.
**Available for Staff tokens**'
requestBody:
required: true
content:
multipart/form-data:
schema:
type: object
properties:
file:
type: string
format: binary
description: 'Audio file to transcribe (max 25MB). Supported formats: mp3, mp4, m4a, wav, webm, flac, ogg.'
model:
type: string
description: Model identifier in provider/model format (e.g., "openai/gpt-4o-transcribe", "openai/whisper-1", "google/chirp-2").
example: openai/gpt-4o-transcribe
language:
type: string
description: ISO-639-1 language code for the audio content (e.g., "en" for English, "es" for Spanish, "he" for Hebrew). When omitted, the provider will auto-detect the language.
prompt:
type: string
description: Optional guiding prompt to improve transcription accuracy. Useful for providing context, domain-specific terminology, or correcting recurring misrecognitions.
response_format:
type: string
enum:
- json
- text
- srt
- verbose_json
- vtt
description: Desired response format. 'json' returns a simple JSON with text, 'text' returns plain text, 'srt' returns SubRip subtitle format, 'verbose_json' returns detailed JSON with word-level timestamps, 'vtt' returns WebVTT subtitle format. Defaults to 'json'.
temperature:
type: number
minimum: 0
maximum: 1
description: Sampling temperature between 0 and 1. Higher values make the output more random, while lower values make it more deterministic. Defaults to 0.
async:
type: boolean
description: Process the request asynchronously. Returns a run UID immediately that can be polled via GET /v3/ai/transcription_runs/{uid}. Recommended for long audio files or when diarization is needed.
default: false
required:
- file
- model
responses:
'200':
description: Successful transcription.
content:
application/json:
schema:
allOf:
- type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
- properties:
data:
type: object
description: Represents an audio transcription result, following the OpenAI Whisper API response format. Contains the transcribed text along with optional metadata such as detected language, audio duration, word-level timestamps, and segment-level data.
properties:
text:
type: string
readOnly: true
description: The full transcribed text output from the audio file.
language:
type: string
readOnly: true
description: The detected or specified language code in ISO-639-1 format (e.g., "en" for English, "es" for Spanish, "he" for Hebrew).
duration:
type: number
readOnly: true
description: Total duration of the audio file in seconds (e.g., 3.5).
words:
type: array
readOnly: true
description: Word-level timestamps for each transcribed word. Only present when using the 'verbose_json' response format.
items:
type: object
properties:
word:
type: string
description: The transcribed word.
start:
type: number
description: Start time of the word in seconds from the beginning of the audio.
end:
type: number
description: End time of the word in seconds from the beginning of the audio.
segments:
type: array
readOnly: true
description: Segment-level data with timing and optional speaker information. Each segment represents a contiguous block of transcribed speech, useful for diarization and long audio files.
items:
type: object
properties:
id:
type: integer
description: Sequential identifier for the segment (e.g., 0, 1, 2).
start:
type: number
description: Start time of the segment in seconds from the beginning of the audio.
end:
type: number
description: End time of the segment in seconds from the beginning of the audio.
text:
type: string
description: The transcribed text for this segment.
speaker:
type: string
description: Speaker identifier when diarization is enabled (e.g., "SPEAKER_00", "SPEAKER_01").
required:
- text
example:
text: For more information visit www.FEMA.gov
language: en
duration: 3.5
words:
- word: For
start: 0
end: 0.18
- word: more
start: 0.18
end: 0.38
- word: information
start: 0.38
end: 0.92
- word: visit
start: 0.92
end: 1.24
- word: www.FEMA.gov
start: 1.24
end: 3.5
segments:
- id: 0
start: 0
end: 3.5
text: For more information visit www.FEMA.gov
speaker: SPEAKER_00
'202':
description: 'Async mode: job queued successfully. Poll the returned run UID for the result.'
content:
application/json:
schema:
allOf:
- type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
- properties:
data:
type: object
description: Represents an async transcription run. Poll this resource until status is COMPLETED or FAILED.
properties:
uid:
type: string
readOnly: true
description: Unique identifier of the transcription run.
status:
type: string
readOnly: true
enum:
- QUEUED
- IN_PROGRESS
- COMPLETED
- FAILED
description: 'Current status of the run. Possible values: ''QUEUED'' (job is waiting to be processed), ''IN_PROGRESS'' (job is actively being processed by the transcription provider), ''COMPLETED'' (job finished successfully and result is available), ''FAILED'' (job encountered an error and error_message is available).'
created_at:
type: string
format: date-time
readOnly: true
description: The date and time when the run was created, in ISO 8601 format (e.g., "2026-02-08T13:18:39.698Z").
updated_at:
type: string
format: date-time
readOnly: true
description: The date and time when the run was last updated, in ISO 8601 format (e.g., "2026-02-08T13:18:41.000Z").
result:
type: object
description: The transcription result. Only present when status is 'COMPLETED'.
properties:
text:
type: string
readOnly: true
description: The full transcribed text output from the audio file.
language:
type: string
readOnly: true
description: The detected or specified language code in ISO-639-1 format (e.g., "en" for English, "es" for Spanish, "he" for Hebrew).
duration:
type: number
readOnly: true
description: Total duration of the audio file in seconds (e.g., 3.5).
words:
type: array
readOnly: true
description: Word-level timestamps for each transcribed word. Only present when using the 'verbose_json' response format.
items:
type: object
properties:
word:
type: string
description: The transcribed word.
start:
type: number
description: Start time of the word in seconds from the beginning of the audio.
end:
type: number
description: End time of the word in seconds from the beginning of the audio.
segments:
type: array
readOnly: true
description: Segment-level data with timing and optional speaker information. Each segment represents a contiguous block of transcribed speech, useful for diarization and long audio files.
items:
type: object
properties:
id:
type: integer
description: Sequential identifier for the segment (e.g., 0, 1, 2).
start:
type: number
description: Start time of the segment in seconds from the beginning of the audio.
end:
type: number
description: End time of the segment in seconds from the beginning of the audio.
text:
type: string
description: The transcribed text for this segment.
speaker:
type: string
description: Speaker identifier when diarization is enabled (e.g., "SPEAKER_00", "SPEAKER_01").
required:
- text
example:
text: For more information visit www.FEMA.gov
language: en
duration: 3.5
words:
- word: For
start: 0
end: 0.18
- word: more
start: 0.18
end: 0.38
- word: information
start: 0.38
end: 0.92
- word: visit
start: 0.92
end: 1.24
- word: www.FEMA.gov
start: 1.24
end: 3.5
segments:
- id: 0
start: 0
end: 3.5
text: For more information visit www.FEMA.gov
speaker: SPEAKER_00
readOnly: true
error_message:
type: string
readOnly: true
description: Error message describing the failure reason. Only present when status is 'FAILED'.
required:
- uid
- status
- created_at
example:
uid: 85ade9f5-2690-48e8-ae5b-b07d6b57b457
status: COMPLETED
created_at: '2026-02-08T13:18:39.698Z'
updated_at: '2026-02-08T13:18:41.000Z'
result:
text: For more information visit www.FEMA.gov
language: en
duration: 3.5
'400':
description: Bad Request - The request is malformed or contains invalid syntax.
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
example:
success: false
errors:
- code: invalid_syntax
message: Request body is malformed or missing required multipart form data.
'401':
description: Unauthorized - The bearer token is missing, expired, or invalid.
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
example:
success: false
errors:
- code: unauthorized
message: Invalid or expired bearer token.
'413':
description: Payload Too Large - The uploaded audio file exceeds the 25MB size limit.
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
example:
success: false
errors:
- field: file
code: too_large
message: File size exceeds the maximum allowed limit of 25MB.
'422':
description: Unprocessable Entity - Validation error with valid syntax.
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
example:
success: false
errors:
- field: model
code: invalid
message: 'Unsupported model. Supported models: openai/whisper-1, openai/gpt-4o-transcribe, google/chirp-2.'
'429':
description: Too Many Requests - Rate limit exceeded (10 requests per minute).
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
description: Indicates whether the API request was successful (true) or failed (false).
data:
type: object
description: 'The response payload. Present on successful responses (success: true).'
error:
type: string
description: Error message for simple error responses. Used in some legacy endpoints.
errors:
type: array
description: 'Array of error objects for detailed error responses. Present on error responses (success: false).'
items:
type: object
properties:
code:
type: string
description: Machine-readable error code (e.g., 'already_exists', 'invalid', 'not_found').
message:
type: string
description: Human-readable error message.
field:
type: string
description: The field that caused the error (for validation errors).
required:
- code
- message
required:
- success
description: Generic wrapper object for API responses. Success responses contain 'data', while error responses contain 'errors' array or 'error' string.
example:
success: false
errors:
- code: rate_limit_exceeded
message: Rate limit exceeded. Maximum 10 requests per minute. Please retry after 60 seconds.
security:
- Bearer: []
operationId: postV3AiAudioTranscriptions
x-operation-id-source: derived
components:
securitySchemes:
Bearer:
type: http
scheme: bearer
bearerFormat: JWT
description: 'Provide a valid bearer token in the Authorization header. Example: ''Authorization: Bearer {app_token}'''
x-provenance:
method: searched
source: https://developers.intandem.tech:443/reference
harvested: '2026-11-15'
tool: harvest-readme-openapi.py
note: Assembled verbatim from the OpenAPI definition ReadMe embeds in each operation page of the provider's developer portal; paths and components merged by API title, nothing authored.
assembled_from:
- https://developers.intandem.tech/reference/businessrulescontroller_createbulkimportjob.md
- https://developers.intandem.tech/reference/businessrulescontroller_createbusinessrule.md
- https://developers.intandem.tech/reference/businessrulescontroller_deletebusinessrule.md
- https://developers.intandem.tech/reference/businessrulescontroller_getbusinessrule.md
- https://developers.intandem.tech/reference/businessrulescontroller_getbusinessrules.md
- https://developers.intandem.tech/reference/businessrulescontroller_gethistory.md
- https://developers.intandem.tech/reference/businessrulescontroller_gethistoryrecord.md
- https://developers.intandem.tech/reference/businessrulescontroller_updatebusinessrule.md
- https://developers.intandem.tech/reference/chatmessagescontroller_createmessage.md
- https://developers.intandem.tech/reference/chatmessagescontroller_getmessages.md
- https://developers.intandem.tech/reference/chatscontroller_createchat.md
- https://developers.intandem.tech/reference/chatscontroller_getchat.md
- https://developers.intandem.tech/reference/chatscontroller_getchats.md
- https://developers.intandem.tech/reference/createaigenerationfeedback.md
- https://developers.intandem.tech/reference/get_v3-ai-ai-recommendations.md
- https://developers.intandem.tech/reference/get_v3-ai-ai-smart-replies.md
- https://developers.intandem.tech/reference/get_v3-ai-chat-completion-runs-uid.md
- https://developers.intandem.tech/reference/get_v3-ai-chat-completion-runs.md
- https://developers.intandem.tech/reference/get_v3-ai-staff-ai-settings-staff-uid.md
- https://developers.intandem.tech/reference/get_v3-ai-transcription-runs-uid.md
- https://developers.intandem.tech/reference/get_v3-ai-transcription-runs.md
- https://developers.intandem.tech/reference/getairecommendation.md
- https://developers.intandem.tech/reference/getbusinessaisettings.md
- https://developers.intandem.tech/reference/post_v3-ai-ai-recommendations.md
# --- truncated at 32 KB (35 KB total) ---
# Full source: https://artifacts.apis.io/vcita/openapi/vcita-ai-audio-transcriptions-api-openapi.yml