Speech to Text: start task
POST/api/technology/speech-to-text-whisper-enhanced
Start an Enhanced Speech to Text Built on Whisper task for a media file.
Enhanced Speech to Text Built on Whisper features
- Multi-channel audio files are supported.
- Channel id is included in individual transcription segments.
- Language for transcription can be specified as a query parameter.
- Language switching can be activated via a query parameter. It is a feature of the Enhanced Speech to Text built on Whisper technology, which identifies the predominant language spoken within each thirty-second interval of audio. The identified language is then utilized for transcribing that particular section.
- To use a specific language as the source, it must be licensed. Otherwise, an error is raised.
- If you use auto-detect or language switching, only licensed languages are considered as the source for the translation. In case the actually detected language is not licensed, the closest licensed language is used instead.
Request
Query Parameters
Possible values: [split
, mix
]
Default value: split
A string enumeration value representing the channel mode for conversion. This value indicates how the audio channels should be processed during conversion. Only the channels with the specified indices (channels
parameter) will be processed, and others will be ignored.
A string of integers separated by comma (without spaces), representing the channels that should be kept during conversion. If specified, only the channels with the specified indices will be processed, and others will be ignored. If empty, all channels in the audio data will be processed. Note that channels
is 0-based.
Default value: auto
A string specifying the language for Enhanced Speech to Text Built
on Whisper. The value should follow RFC 5646.
It can consist of the "language", "region", and "privateuse" subtags. Use auto
for
automatic detection of the language.
Refer to supported languages
for a complete list of supported language tags.
By default, the language of the audio is detected once at the
beginning of processing. Setting language_switching
to true allows for dynamic
language switching in the audio, with the language being detected approximately
every 30 seconds.
Header Parameters
Correlation ID is a special type of request ID which is unique over a series of requests and responses, identifying a transaction in a distributed system. Correlation ID will be generated if not provided.
In distributed system architecture (microservices architecture) it is a unique ID of request and response combination throughout all components of a distributed system. Request ID will be generated if not provided.
- multipart/form-data
Bodyrequired
required
Input media file.
Responses
- 202
- 400
- 403
- 413
- 422
- 429
- 507
Speech to Text task was accepted. Follow the X-Location
header to poll for the task state.
Response Headers
X-Location
string
Example: /api/technology/speech-to-text-whisper-enhanced/123e4567-e89b-12d3-a456-426614174000
A URL the client should poll for task state and result.
- application/json
- Schema
- Example (from schema)
Schema
task
object
required
Possible values: [pending
, running
, rejected
, failed
, done
]
{
"task": {
"task_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"state": "pending"
}
}
Request payload data was invalid and could not be parsed.
- application/json
- Schema
- Example (from schema)
- request.invalid
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Invalid request.
{
"type": "request.invalid",
"message": "Invalid request.",
"detail": []
}
Request is forbidden.
- application/json
- Schema
- Example (from schema)
- request.forbidden
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Processing capacity allowed for the operation was exceeded.
{
"type": "request.forbidden",
"message": "Request is forbidden.",
"detail": [
{
"location": [
"license"
],
"message": "Licensed processing capacity exceeded.",
"type": "licensing.capacity-exceeded",
"context": {}
}
]
}
The request entity (payload) size exceeds the allowed limit.
- application/json
- Schema
- Example (from schema)
- request.size-limit-exceeded
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Request size limit exceeded.
{
"type": "request.size-limit-exceeded",
"message": "Request size limit exceeded.",
"detail": [
{
"location": [
"body",
"file"
],
"message": "Input media file too large.",
"type": "media.too-large",
"context": {
"file_size": 1048576000,
"max_file_size": 524288000,
"size_unit": "bytes"
}
}
]
}
Error during validation of request payload data occurred.
- application/json
- Schema
- Example (from schema)
- request validation error
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Request validation error.
{
"type": "request.validation-error",
"message": "Request validation error.",
"detail": []
}
Request rate limit exceeded.
The request may be retried after a while. The following response headers may be checked for details: retry-after
, x-ratelimit-limit
, x-ratelimit-remaining
, x-ratelimit-reset
.
Response Headers
retry-after
number
Header indicates how long the user agent should wait before making a follow-up request.
x-ratelimit-limit
number
Size of the current rate limiting window.
x-ratelimit-remaining
number
Remaining number of requests in the current rate limiting window.
x-ratelimit-reset
number
Time at which the current rate limiting window resets (in UTC epoch).
- application/json
- Schema
- Example (from schema)
- request.rate-limit-exceeded
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Rate limit exceeded.
{
"type": "request.rate-limit-exceeded",
"message": "Rate limit exceeded: 1 per 5 second.",
"detail": []
}
The storage is full and cannot accept any data.
- application/json
- Schema
- Example (from schema)
- insufficient storage
Schema
Array [
Array [
- MOD1
- MOD2
]
- MOD1
- MOD2
- MOD3
- MOD4
]
Possible values: [internal
, resource.not-found
, method.invalid
, request.forbidden
, request.invalid
, request.validation-error
, request.rate-limit-exceeded
, request.size-limit-exceeded
, storage.capacity-exceeded
]
Machine-readable error type.
Human-readable summary of the error.
detail
object[]
Optional higher level of detail. It is intended for better understanding of the error or advanced error handling.
location
object[]
required
Location of the error.
anyOf
integer
string
Human-readable summary of the error.
Machine-readable error type.
context
object
Optional key-value object with additional context
property name*
object
anyOf
string
integer
number
boolean
{
"type": "internal",
"message": "string",
"detail": [
{
"location": [
0,
"string"
],
"message": "string",
"type": "string",
"context": {}
}
]
}
Storage capacity exceeded.
{
"type": "storage.capacity-exceeded",
"message": "Storage capacity exceeded.",
"detail": []
}