How-to guides

Perform speech recognition

• Transcribe short audio files

  Perform synchronous speech recognition on local and remote audio files.

• Transcribe audio from streaming input

  Perform streaming speech recognition on local audio files.

• Transcribe long audio files

  Perform batch speech recognition on local and remote audio files.

Configuring recognition requests

• Create and use Recognizers

  Store and reuse recognition configuration using Recognizers.

• Automatically detect spoken language

  Provide multiple language codes for audio transcription requests sent to Cloud Speech-to-Text.

• Select a transcription model

  Select a specialized machine learning model for audio transcription.

• Transcribe audio with multiple-channels

  Transcribe audio files that include more than one channel.

• Get automatic punctuation

  Include punctuation in transcription results from Speech-to-Text.

• Enable word-level confidence

  Specify that transcriptions should contain an accuracy indication for individual words.

• Enable spoken punctuation and spoken emojis

  Perform speech recognition on a remote file and include time offset (timestamp) values for recognized words.

• Encrypt Speech-to-Text resources

  Encrypt Speech-to-Text resources using customer-managed encryption keys (CMEK).

Learn about transcription models

• Transcribe audio with Chirp

  Perform speech recognition using Chirp, the latest universal speech model.

• Transcribe audio with medical models

  Perform speech recognition using models tuned for medical dictation and medical conversation.

• Base64 encoding

  Learn how to base64 encode audio.