Speech2TxtResult

The Speech2TxtResult object containing speech-to-text transcription results.

Attributes

text (String)

A string containing the transcribed text from the audio.

model (String)

An optional string naming the model that produced the transcript.

language (String)

An optional string containing the detected or specified language of the audio. With Gemini, this field contains the language option you passed and is omitted otherwise. For OpenAI and xAI, whether it is present depends on the provider response.

segments (Array)

An optional array of segment objects containing detailed transcription information.

duration (Number)

An optional duration of the audio in seconds. Provider-dependent (e.g. returned by xAI).

words (Array)

An optional array of per-word timestamp objects. Provider-dependent (returned by xAI, and by Gemini when you pass timestamp_granularities: ['word'] or diarize: true). Each word has:

• text (String): The transcribed word.
• start (Number): Start time of the word in seconds.
• end (Number): End time of the word in seconds.
• speaker (String): Detected speaker, present when diarize: true and the provider labels the word (for example spk:0 on Gemini).