Deepgram · Schema
Deepgram Transcript
Schema representing a Deepgram transcription response including metadata, channel results, utterances, and audio intelligence features such as sentiment, topics, intents, and summarization.
Artificial IntelligenceSpeech-To-TextText-To-SpeechTranscriptionVoice AI
Properties
| Name | Type | Description |
|---|---|---|
| metadata | object | |
| results | object |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://deepgram.com/schemas/deepgram/transcript.json",
"title": "Deepgram Transcript",
"description": "Schema representing a Deepgram transcription response including metadata, channel results, utterances, and audio intelligence features such as sentiment, topics, intents, and summarization.",
"type": "object",
"required": ["metadata", "results"],
"properties": {
"metadata": {
"$ref": "#/$defs/Metadata"
},
"results": {
"$ref": "#/$defs/Results"
}
},
"$defs": {
"Metadata": {
"type": "object",
"description": "Metadata about the transcription request and audio file.",
"properties": {
"transaction_key": {
"type": "string",
"description": "Unique identifier for the transaction."
},
"request_id": {
"type": "string",
"description": "Unique identifier for the API request."
},
"sha256": {
"type": "string",
"description": "SHA-256 hash of the submitted audio."
},
"created": {
"type": "string",
"format": "date-time",
"description": "Timestamp when the request was created."
},
"duration": {
"type": "number",
"description": "Duration of the submitted audio in seconds.",
"minimum": 0
},
"channels": {
"type": "integer",
"description": "Number of audio channels detected.",
"minimum": 1
},
"models": {
"type": "array",
"items": {
"type": "string"
},
"description": "Model identifiers used for transcription."
},
"model_info": {
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/ModelInfo"
},
"description": "Detailed information about models used, keyed by model UUID."
}
}
},
"ModelInfo": {
"type": "object",
"description": "Information about a specific model used for transcription.",
"properties": {
"name": {
"type": "string",
"description": "Name of the model."
},
"version": {
"type": "string",
"description": "Version of the model."
},
"arch": {
"type": "string",
"description": "Architecture of the model."
}
}
},
"Results": {
"type": "object",
"description": "Transcription results and audio intelligence analysis.",
"properties": {
"channels": {
"type": "array",
"items": {
"$ref": "#/$defs/Channel"
},
"description": "Transcription results organized by audio channel."
},
"utterances": {
"type": "array",
"items": {
"$ref": "#/$defs/Utterance"
},
"description": "Transcription results organized by utterance."
},
"summary": {
"$ref": "#/$defs/Summary"
},
"sentiments": {
"$ref": "#/$defs/SentimentResults"
},
"topics": {
"$ref": "#/$defs/TopicResults"
},
"intents": {
"$ref": "#/$defs/IntentResults"
}
}
},
"Channel": {
"type": "object",
"description": "Transcription data for a single audio channel.",
"properties": {
"alternatives": {
"type": "array",
"items": {
"$ref": "#/$defs/Alternative"
},
"description": "Alternative transcriptions ordered by confidence."
},
"detected_language": {
"type": "string",
"description": "Detected language of the audio in this channel.",
"pattern": "^[a-z]{2}(-[A-Z]{2})?$"
},
"language_confidence": {
"type": "number",
"description": "Confidence score for the detected language.",
"minimum": 0,
"maximum": 1
}
}
},
"Alternative": {
"type": "object",
"description": "A single transcription alternative with confidence score.",
"properties": {
"transcript": {
"type": "string",
"description": "Full transcript text for this alternative."
},
"confidence": {
"type": "number",
"description": "Confidence score for this alternative.",
"minimum": 0,
"maximum": 1
},
"words": {
"type": "array",
"items": {
"$ref": "#/$defs/Word"
},
"description": "Individual words with timing and confidence information."
},
"paragraphs": {
"$ref": "#/$defs/ParagraphGroup"
}
}
},
"Word": {
"type": "object",
"description": "A single transcribed word with timing and metadata.",
"required": ["word", "start", "end", "confidence"],
"properties": {
"word": {
"type": "string",
"description": "The transcribed word."
},
"start": {
"type": "number",
"description": "Start time of the word in seconds.",
"minimum": 0
},
"end": {
"type": "number",
"description": "End time of the word in seconds.",
"minimum": 0
},
"confidence": {
"type": "number",
"description": "Confidence score for this word.",
"minimum": 0,
"maximum": 1
},
"speaker": {
"type": "integer",
"description": "Speaker identifier when diarization is enabled.",
"minimum": 0
},
"punctuated_word": {
"type": "string",
"description": "The word with punctuation applied."
},
"sentiment": {
"type": "string",
"enum": ["positive", "negative", "neutral"],
"description": "Sentiment of the word when sentiment analysis is enabled."
},
"sentiment_score": {
"type": "number",
"description": "Sentiment confidence score for this word.",
"minimum": -1,
"maximum": 1
}
}
},
"ParagraphGroup": {
"type": "object",
"description": "Transcript organized into paragraphs.",
"properties": {
"transcript": {
"type": "string",
"description": "Full transcript organized into paragraphs."
},
"paragraphs": {
"type": "array",
"items": {
"$ref": "#/$defs/Paragraph"
},
"description": "Individual paragraph objects."
}
}
},
"Paragraph": {
"type": "object",
"description": "A paragraph segment of the transcript.",
"properties": {
"sentences": {
"type": "array",
"items": {
"$ref": "#/$defs/Sentence"
},
"description": "Sentences within this paragraph."
},
"start": {
"type": "number",
"description": "Start time of the paragraph in seconds.",
"minimum": 0
},
"end": {
"type": "number",
"description": "End time of the paragraph in seconds.",
"minimum": 0
},
"num_words": {
"type": "integer",
"description": "Number of words in this paragraph.",
"minimum": 0
},
"speaker": {
"type": "integer",
"description": "Speaker identifier for this paragraph.",
"minimum": 0
}
}
},
"Sentence": {
"type": "object",
"description": "A sentence within a paragraph.",
"properties": {
"text": {
"type": "string",
"description": "Sentence text."
},
"start": {
"type": "number",
"description": "Start time of the sentence in seconds.",
"minimum": 0
},
"end": {
"type": "number",
"description": "End time of the sentence in seconds.",
"minimum": 0
}
}
},
"Utterance": {
"type": "object",
"description": "A speech utterance segment with speaker and timing information.",
"properties": {
"id": {
"type": "string",
"description": "Unique identifier for this utterance."
},
"start": {
"type": "number",
"description": "Start time of the utterance in seconds.",
"minimum": 0
},
"end": {
"type": "number",
"description": "End time of the utterance in seconds.",
"minimum": 0
},
"confidence": {
"type": "number",
"description": "Confidence score for this utterance.",
"minimum": 0,
"maximum": 1
},
"channel": {
"type": "integer",
"description": "Audio channel index for this utterance.",
"minimum": 0
},
"transcript": {
"type": "string",
"description": "Transcript text for this utterance."
},
"words": {
"type": "array",
"items": {
"$ref": "#/$defs/Word"
},
"description": "Individual words within this utterance."
},
"speaker": {
"type": "integer",
"description": "Speaker identifier for this utterance.",
"minimum": 0
}
}
},
"Summary": {
"type": "object",
"description": "Summary of the transcribed or analyzed content.",
"properties": {
"short": {
"type": "string",
"description": "Short summary of the content."
}
}
},
"SentimentResults": {
"type": "object",
"description": "Sentiment analysis results for the content.",
"properties": {
"segments": {
"type": "array",
"items": {
"$ref": "#/$defs/SentimentSegment"
},
"description": "Sentiment analysis for individual segments."
},
"average": {
"$ref": "#/$defs/SentimentAverage"
}
}
},
"SentimentSegment": {
"type": "object",
"description": "Sentiment analysis for a single content segment.",
"properties": {
"text": {
"type": "string",
"description": "Text of the segment."
},
"start_word": {
"type": "integer",
"description": "Index of the first word in this segment.",
"minimum": 0
},
"end_word": {
"type": "integer",
"description": "Index of the last word in this segment.",
"minimum": 0
},
"sentiment": {
"type": "string",
"enum": ["positive", "negative", "neutral"],
"description": "Overall sentiment of the segment."
},
"sentiment_score": {
"type": "number",
"description": "Confidence score for the sentiment classification.",
"minimum": -1,
"maximum": 1
}
}
},
"SentimentAverage": {
"type": "object",
"description": "Average sentiment across all segments.",
"properties": {
"sentiment": {
"type": "string",
"enum": ["positive", "negative", "neutral"],
"description": "Overall average sentiment."
},
"sentiment_score": {
"type": "number",
"description": "Average sentiment score.",
"minimum": -1,
"maximum": 1
}
}
},
"TopicResults": {
"type": "object",
"description": "Topic detection results for the content.",
"properties": {
"segments": {
"type": "array",
"items": {
"$ref": "#/$defs/TopicSegment"
},
"description": "Topic detection for individual segments."
}
}
},
"TopicSegment": {
"type": "object",
"description": "Topic detection for a single content segment.",
"properties": {
"text": {
"type": "string",
"description": "Text of the segment."
},
"start_word": {
"type": "integer",
"description": "Index of the first word in this segment.",
"minimum": 0
},
"end_word": {
"type": "integer",
"description": "Index of the last word in this segment.",
"minimum": 0
},
"topics": {
"type": "array",
"items": {
"$ref": "#/$defs/Topic"
},
"description": "Topics detected in this segment."
}
}
},
"Topic": {
"type": "object",
"description": "A detected topic with confidence score.",
"properties": {
"topic": {
"type": "string",
"description": "Detected topic label."
},
"confidence_score": {
"type": "number",
"description": "Confidence score for the topic detection.",
"minimum": 0,
"maximum": 1
}
}
},
"IntentResults": {
"type": "object",
"description": "Intent recognition results for the content.",
"properties": {
"segments": {
"type": "array",
"items": {
"$ref": "#/$defs/IntentSegment"
},
"description": "Intent recognition for individual segments."
}
}
},
"IntentSegment": {
"type": "object",
"description": "Intent recognition for a single content segment.",
"properties": {
"text": {
"type": "string",
"description": "Text of the segment."
},
"start_word": {
"type": "integer",
"description": "Index of the first word in this segment.",
"minimum": 0
},
"end_word": {
"type": "integer",
"description": "Index of the last word in this segment.",
"minimum": 0
},
"intents": {
"type": "array",
"items": {
"$ref": "#/$defs/Intent"
},
"description": "Intents detected in this segment."
}
}
},
"Intent": {
"type": "object",
"description": "A detected intent with confidence score.",
"properties": {
"intent": {
"type": "string",
"description": "Detected intent label."
},
"confidence_score": {
"type": "number",
"description": "Confidence score for the intent recognition.",
"minimum": 0,
"maximum": 1
}
}
}
}
}