Features

Get precise timing information for each word in the transcription with confidence scores

Automatically detect the language of the audio

Get sentence-level transcription segments with timing information

Automatically redact personally identifiable information and payment card information

Identify and label different speakers in the audio with speaker confidence scores

Boost recognition accuracy for specific words, brand names, and domain terms

Control punctuation and capitalization formatting in transcripts

Control how long Pulse waits after speech ends before finalizing the transcript

Convert spoken-form numbers, dates, and currencies into written form

Take manual control of when transcripts are finalized using finalize_on_words and max_words

Emit acoustic speech_started / speech_ended frames interleaved with the transcription stream. Independent of transcript finalization.

Tune the end-of-utterance silence timeout with eou_timeout_ms for interactive vs dictation-style workloads.

Optional per-speaker age and gender inference alongside the transcript.

Optional per-utterance emotion classification alongside the transcript.