transcription

TBD

TOOLTRANSCRIBE_AUDIO

Transcribe Audio

Parameters for the web search request.

Required attributes

Name
url
Type
string
Description
URL to a Gladia file or to an external audio or video file.
http://files.gladia.io/example/audio-transcription/split_infinity.wav

Optional attributes

Name
context_prompt
Type
string
Description
Context to feed the transcription model with for possible better performance.
Name
custom_vocabulary
Type
array[string]
Description
Specific vocabulary list to feed the transcription model with.
Name
language
Type
string
Description
Set the spoken language for the given audio (ISO 639 standard).
en
Name
speakers
Type
integer
Description
Number of speakers in the audio. Leave to 0 for automatic detection.
2
Name
custom_spelling
Type
object
Description
Dictionary for custom spellings.
{{\'SQL\': [\'Sequel\']}}

Function Call

TOOL

TRANSCRIBE_AUDIO

#### TRANSCRIBE_AUDIO
```json
{
  "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
}
```

Response

#### Success

TEXTLAST_TRANSCRIPTConversation

Last Transcript

The last transcript.

Conversation Variable

TEXT

{LAST_TRANSCRIPT}

**Speaker 1**: Hello, how are you?
**Speaker 2**: I am fine, thank you.

TEXTLAST_TRANSCRIPT_JSONConversation

Last Transcript Json

The last transcript escaped for usage inside a json string.

Conversation Variable

TEXT

{LAST_TRANSCRIPT_JSON}

**Speaker 1**: Hello, how are you?\n**Speaker 2**: I am fine, thank you.