V-Blaze Online Help

Common Tags

Table 1. Common /transcribe API Parameters for V‑Blaze

Name

Type

Values

Description

callback (optional)

string

URL: HTTP or HTTPS are supported

The URL to which the transcription results will be POSTed. A callback is the address and (optionally) method name and parameters of a web application that can receive data via HTTP or HTTPS. Callbacks are usually used to enable another application to receive and directly interact with the transcripts produced.

V‑Blaze transcriptions are normally returned immediately and directly to the user or application that submitted the audio file for transcription. When a callback is specified, the transcription result is POSTed to the specified callback address and not returned in the response. V‑Blaze does not retry failed callbacks.

file (required)

 

LPCM audio data in WAVE or RAW format

A single audio file to process.

model (optional) –

string

see language models

Indicates which language model should be used to transcribe the audio. If not specified, the default model will be used. Refer to model for more information on this parameter.

output (optional)

string

Values: json (default), jsontop, text

Indicates the desired output format. Refer to output for more information on this parameter.

requestid

string

The unique identifier for the request for tracing purposes. This can be specified as a parameter or in the X-Request-Id HTTP header. If a requestid is provided in one of these ways, the specified requestid is included in JSON output and in the WebAPI access log.

Refer to requestid for WebAPI for more information on how to use requestid.



Table 2. Common /transcribe API Parameters for V‑Cloud

Name

Type

Values

Description

callback (optional)

string

URL: HTTP or HTTPS are supported

The URL to which the transcription results will be POSTed. A callback is the address and (optionally) method name and parameters of a web application that can receive data via HTTP or HTTPS. Callbacks are usually used to enable another application to receive and directly interact with the transcripts produced.

Once a callback returns success (indicated by HTTP code 200), the result is no longer available from V‑Cloud . If a callback fails, it will be retried until it succeeds or until a maximum number of retries is reached.

file (required)

string

Supported zip file formats are zip (MIME type application/zip) and 7z (MIME type application/x-7z-compressed).

The zip file can be password encrypted, with the zpass parameter specifying the password.

Supported audio formats are WAVE LPCM and ITU G.711

A single audio file or zip file that contains one or more audio files to process.

The Linux file command gives the following outputs for accepted audio file formats:

$ file example1.wav
example1.wav: RIFF (little-endian) data, WAVE audio, Microsoft PCM, 8 bit, mono 8000 Hz

$ file example2.wav
example2.wav: RIFF (little-endian) data, WAVE audio, ITU G.711 mu-law, mono 8000 Hz

$ file example3.wav
example3.wav: RIFF (little-endian) data, WAVE audio, ITU G.711 A-law, mono 8000 Hz

The key compatibility indicators are WAVE LPCM and ITU G.711. The sample rate may be between 8000 and 16000 Hz, where 8000 Hz is preferable. The file may also contain more than one channel.

Tip

Transcoding from other audio formats is available as an optional licensed feature. See transcode for more information.

model (optional)

string

see language models

The model parameter is used to specify the language model(s) to use for transcription. The value that you specify for this parameter can be a single language model to transcribe all channels. If you did not specify a model when transcribing audio, the default (eng1:callcenter) model would be used. Voci works with customers to ensure that their deployment delivers the best results possible, providing the language models that are most closely associated with the types of audio that each customer is transcribing. You will receive model names which are authorized for your account from Voci Support.

output (optional)

string

Values: json (default), jsontop, text

Indicates the desired output format. Refer to output for more information on this parameter.

token (required)

string

Used to authenticate and authorize the request. You will receive a token from Voci Support to use with requests to the ASR server. All requests made with your token will be tied to your account. Please notify Voci Support immediately if your token is compromised or lost.

requestid

string

The unique identifier for the request about which you want to retrieve results or status information. This is auto-generated and appears in the JSON output.