All Speech-to-Text code samples

This page contains code samples for Speech-to-Text. To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.

Asynchronously transcribe a local audio file

Perform asynchronous transcription on a local audio file.

Go Java Node.js PHP Python Ruby

View sample

View in documentation

• Transcribing long audio files

Asynchronously transcribe an audio file in Cloud Storage

Perform asynchronous transcription on an audio file stored in Cloud Storage.

Go Java Node.js PHP Python Ruby

View sample

View in documentation

• Transcribing long audio files

Asynchronously transcribe an audio file with time offsets

Perform asynchronous transcription including time offsets on an audio file stored in Cloud Storage.

Go Java Node.js PHP Python Ruby

View sample

Create an asynchronous speech file

Creates an asynchronous speech file.

C++

View sample

Make an audio transcription request

Transcribe a local audio file synchronously.

Go Java Node.js PHP Python

View sample

View in documentation

• Quickstart: Using client libraries

Make an audio transcription request (beta)

Transcribe a local audio file synchronously.

Java Python

View sample

Recognize a synchronization request

Loads the audio file from the disk into the request.

C++

View sample

Streaming speech recognition

Reads and writes audio from a file.

C++

View sample

Streaming speech recognition with punctuation

Performs streaming speech recognition on raw PCM audio data.

Java

View sample

Synchronously recognize Cloud Storage

Creates a stub connected to the Speech-to-Text service.

C++

View sample

Synchronously recognize words

Detects speech in the audio file.

Node.js Ruby

View sample

Synchronously recognizes punctuation

Performs transcription with automatic punctuation on raw PCM audio data.

Java

View sample

Synchronously transcribe a Cloud Storage file

Perform a synchronous transcription on an audio file stored in Cloud Storage

Go Java Node.js PHP Python Ruby

View sample

Synchronously transcribe a local file

Perform synchronous transcription on a local audio file.

Go Java Node.js PHP Python Ruby

View sample

Transcribe a file in Cloud Storage using a transcription model

Transcribe an audio file in Cloud Storage using a trained transcription model.

Java Node.js Python

View sample

View in documentation

• Selecting a transcription model

Transcribe a file in Cloud Storage with word-level confidence (beta)

Transcribe an audio file stored in Cloud Storage, returning the confidence level for each word.

Node.js

View sample

Transcribe a file with word-level confidence (beta)

Transcribe an audio file, returning the confidence level for each word.

Java Node.js Python

View sample

Transcribe a local file

Transcribe a short audio file.

Python

View sample

Transcribe a local file using a transcription model

Transcribe a local audio file using a trained transcription model.

Go Java Node.js PHP Python Ruby

View sample

View in documentation

• Selecting a transcription model

Transcribe a local file using an enhanced speech recognition (beta)

Transcribe a local audio file, where you specify an enhanced model.

Python

View sample

Transcribe a local file using an enhanced speech recognition model

Transcribe a local audio file, where you specify an enhanced model.

Go Java Node.js PHP Python Ruby

View sample

Transcribe a local file with auto punctuation

Transcribe a local audio file, including auto punctuation.

Go Java Node.js PHP Python Ruby

View sample

View in documentation

• Getting automatic punctuation

Transcribe a local file with auto punctuation (beta)

Transcribe a local audio file, including auto punctuation.

Java Python

View sample

Transcribe a local file with recognition metadata (beta)

Transcribe a local audio file, including recognition metadata in the response.

Java Node.js Python

View sample

Transcribe a local multi-channel file

Transcribe a local audio file that includes more than one channel.

Java Node.js Python Ruby

View sample

Transcribe a local multi-channel file (beta)

Transcribe a local audio file that includes more than one channel.

Go Node.js Python

View sample

Transcribe a local multi-lingual file (beta)

Transcribe a local audio file that includes more than one language.

Java Node.js Python

View sample

Transcribe a multi-channel file in Cloud Storage

Transcribe an audio file stored in Cloud Storage that includes more than one channel.

Java Node.js Python Ruby

View sample

Transcribe a multi-channel file in Cloud Storage (beta)

Transcribe an audio file stored in Cloud Storage that includes more than one channel.

Node.js

View sample

Transcribe a multi-lingual file in Cloud Storage (beta)

Transcribe an audio file stored in Cloud Storage that includes more than one language.

Node.js

View sample

Transcribe a streaming audio feed

Transcribe a streaming audio feed from a microphone.

Java Node.js Python

View sample

Transcribe a streaming feed on a local file

Transcribe a streaming audio feed from a microphone on a local file.

Go Java Node.js PHP Python Ruby

View sample

View in documentation

• Transcribing audio from streaming input

Transcribe streaming audio from a microphone

Transcribe streaming audio from a microphone.

Go Java Node.js Python

View sample

View in documentation

• Transcribing audio from streaming input

Transcription of a file in Cloud Storage with diarization

Recognize multiple speakers in an audio file stored in Cloud Storage.

Java

View sample

Transcription of a file in Cloud Storage with diarization (beta)

Recognize multiple speakers in an audio file stored in Cloud Storage.

Node.js

View sample

Transcription of a local file with diarization

Recognize multiple speakers in a local audio file.

Java Node.js Python

View sample

Transcription with diarization

Identify the different speakers in the audio sample.

Java Node.js

View sample

Try it for yourself

If you're new to Google Cloud, create an account to evaluate how Speech-to-Text performs in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Try Speech-to-Text free