DocumentationAPI ReferenceSelf HostClient LibrariesChangelog
DocumentationAPI ReferenceSelf HostClient LibrariesChangelog
  • Getting Started
    • Introduction
    • Models
    • Authentication
    • HTTP Streaming
  • Text to Speech
    • Overview
    • Quickstart
    • How to TTS
    • Stream TTS
    • Pronunciation Dictionaries
    • Voice Models & Languages
  • Speech to Text
    • Overview
    • Quickstart
  • Cookbooks
    • Speech to Text
  • Voice Cloning
    • Types of Cloning
    • Voice Clone via UI
    • How to Voice Clone
    • Delete Cloned Voice
    • Professional Voice Cloning
  • Integrations
    • LiveKit
    • Plivo
    • Vonage
  • Best Practices
    • Voice Cloning Best Practices
    • PVC Best Practices
    • TTS Best Practices
On this page
  • Available Features
Speech to TextPre-Recorded

Features

|View as Markdown|Open in Claude|

The Pre-Recorded Pulse STT API supports the following features:

Available Features

Word Timestamps

Get precise timing information for each word in the transcription

Language Detection

Automatically detect the language of the audio

Diarization

Identify and label different speakers in the audio

Age & Gender Detection

Predict demographic attributes alongside transcription

Emotion Detection

Detect emotional tone in the transcribed speech

Was this page helpful?
Previous

Webhooks

Next

Troubleshooting

Built with
LogoLogo
AtomsWaves
AtomsWaves