published AI Powered

Google Cloud Speech-to-Text API

The Google Cloud Speech-to-Text API enables developers to convert spoken audio into accurate transcribed text, suitable for building voice assistants and transcription services.

View Source

null%Uptime

nullmsLatency

0Stars

API KeyAuth

NoCredit Card

RESTStyle

v1Version

API Endpoints

Reference for available routes, request structures, and live examples.

Convert speech to text using Google Cloud Speech-to-Text

Full Endpoint URL

https://speech.googleapis.com/v1/speech:recognize

Implementation Example

curl -X POST 'https://speech.googleapis.com/v1/speech:recognize' \
  -H 'Authorization: Bearer YOUR_API_KEY'

Request Payload

{
  "audio": {
    "content": "base64_encoded_audio"
  },
  "config": {
    "encoding": "LINEAR16",
    "sampleRateHertz": 16000
  }
}

Expected Response

{
  "results": [
    {
      "alternatives": [
        {
          "transcript": "Hello, world!"
        }
      ]
    }
  ]
}

Version:v1

Limit:60 minutes/month (free tier)

Real-World Applications

{'items': ['Building voice‑powered assistants that respond to user commands'Optimized Capability
'Transcribing recorded meetingsOptimized Capability
interviewsOptimized Capability
or podcasts'Optimized Capability
'Live captioning for streaming or video content'Optimized Capability
'Analyzing call center audio for sentiment and trends']}Optimized Capability

API Specifications

Pricing Model

Free

Credit Card

Not Required

Response Formats

{'items': ['JSON']}

Supported Languages

7 Languages

SDK Support

REST Only

Rate Limit

600 requests per minute per project

Use Case: Best For

Not Recommended For

Resources

Documentation Source Code

#speech-recognition#audio-transcription#voice-commands

Explore Related APIs

Discover similar APIs to Google Cloud Speech-to-Text API

View All APIs

FREEMIUM

Async.ai API

The Async.ai API provides developers with advanced voice cloning and text-to-speech capabilities, facilitating the creation of realistic audio experiences in applications.

Speech & AudioView Details