{"$schema":"https://json-schema.org/draft/2020-12/schema","type":"object","properties":{"text":{"description":"The transcribed text.","type":"string"},"words":{"description":"Word-level timestamps and confidence scores.","anyOf":[{"type":"array","items":{"type":"object","properties":{"text":{"type":"string"},"start":{"type":"number"},"end":{"type":"number"},"confidence":{"type":"number"},"speaker":{"anyOf":[{"type":"string"},{"type":"null"}]}},"required":["text","start","end","confidence"],"additionalProperties":false}},{"type":"null"}]},"utterances":{"description":"Speaker-separated utterances (when speaker_labels is enabled).","anyOf":[{"type":"array","items":{"type":"object","properties":{"text":{"type":"string"},"start":{"type":"number"},"end":{"type":"number"},"confidence":{"type":"number"},"speaker":{"type":"string"}},"required":["text","start","end","confidence","speaker"],"additionalProperties":false}},{"type":"null"}]},"confidence":{"description":"Overall confidence score for the transcription.","anyOf":[{"type":"number"},{"type":"null"}]},"language_code":{"description":"Detected or specified language code.","anyOf":[{"type":"string"},{"type":"null"}]},"language_confidence":{"description":"Confidence score for language detection.","anyOf":[{"type":"number"},{"type":"null"}]}},"required":["text"],"additionalProperties":false}