Vatis Docs
Speech to Text
- Multilingual Code Switch
- Utterance End
- Pre-recorded
- Real-time
Audio Intelligence
Infrastructure
- Streams
- Diagrams
- Data retention
- Stream templates
- Configuration patches
Speaker Diarization (Romanian)
Pre-recorded transcription with speaker diarization specifications of Romanian-only files using the Vatis Streams API
Stream configuration template ids
- production:
678e375095f8f5742e8718f5
Input data
- multimedia content:
wav,mp3,mp4,webm,flv, etc. - public
httporhttpslink to multimedia file encoded inUTF-8
Egress responses
Export response
Parameters
A disfluency is a part of speech not being smooth and continuous. When disfluencies are disabled (default), all this discontinuous parts from the transcript are removed.
Add punctuation and capitalization to the transcription.
Convert the numerals from their word form to their numeric form (e.g. twenty two -> 22).
Enable or disable splitting stereo audio into two mono audio streams. Possible values: true or false.
Enable the find-replace functionality performed using the user-defined findReplaceExpressions.
Find-replace expressions.
The replace string.
Regex expressions to find.
Replacement merge strategy relative to the left and right neighbours.
STANDALONE: keep the replacement as a standalone wordMERGE_LEFT: concatenate the replacement with the left neighbourMERGE_RIGHT: concatenate the replacement with the right neighbourMERGE_LEFT_RIGHT: concatenate the replacement with both the left and the right neighboursMERGE_LEFT_CAPITALIZE_NEXT: concatenate the replacement with the left neighbour and capitalize the right neighbour
Flag to enable this current expression in the find-replace operation.
splitStereo parameter should not be used in this configurationThe number of speakers to diarize the audio to. When not specified, it is automatically detected.
The minimum number of speakers to diarize the audio to.
The maximum number of speakers to diarize the audio to.
Create a summary based on the upstream content.
Summary length. Options are: brief or detailed.
Summary tone. Options are: conversational or informative.
Summary structure. Options are: paragraphs or bullet_points.
Perform sentiment analysis on the upstream content.
Specifies the custom prompt content for one of the ask0, ask1, …, askN ask anything slots.
When the content is specified, the prompt is considered activated. Otherwise, it is deactivated.
Specifies the custom system prompt for one of the ask0System, ask1System, …, askNSystem ask anything slots.
Specifies the prompt id for one of the ask0Id, ask1Id, …, askNId ask anything slots.
The role of the prompt id is to identify the prompt in the responses.
When unspecified, it will fallback on the index of the slot (e.g. "0", "1").
Specifies the prompt response JSON Schema encoded as a string for one of the ask0Format, ask1Format, …, askNFormat ask anything slots.
When unspecified, the response not be structured in any particular way. When specified, the response will be a JSON object encoded as a string.