See how Deepgram stacks up. Check out our ASR Comparison Tool. 🍎🍊

How developers build with voice

The fastest, most accurate, most reliable, and most scalable speech-to-text API.

Get Started Free Contact Sales

No credit card required. Integrate in minutes.

Built for developers. Trusted by developers.
Built for developers. Trusted by developers.
Deepgram

You’re in good company

Join our community of Speech-to-Text API users all over the globe. Use one of our SDKs to get started in your favorite programming language.

View Customers

const { Deepgram } = require('@deepgram/sdk');
const deepgram = new Deepgram('YOUR_DEEPGRAM_API_KEY');
deepgram.transcription.preRecorded({ url: 'URL_TO_FILE' })
  .then((transcript) ⟹ {
    console.log(transcript);
  })
  .catch((err) ⟹ {
    console.log(err);
  });
{
  "channel_index": [
    {
      "channel": "string",
      "num_channels": 0
    }
  ],
  "duration": 0,
  "start": "string",
  "is_final": true,
  "channel": {
    "alternatives": [
      {
        "transcript": "string",
        "confidence": 0,
        "words": [
          {
            "word": "string",
            "start": 0,
            "end": 0,
            "confidence": 0
          }
        ]
      }
    ]
  }
}
from deepgram import Deepgram
dg_client = Deepgram({ 'api_key': 'YOUR_DEEPGRAM_API_KEY' })
res = await dg_client.transcription.prerecorded({ 'url': 'URL_TO_FILE' })
{
  "channel_index": [
    {
      "channel": "string",
      "num_channels": 0
    }
  ],
  "duration": 0,
  "start": "string",
  "is_final": true,
  "channel": {
    "alternatives": [
      {
        "transcript": "string",
        "confidence": 0,
        "words": [
          {
            "word": "string",
            "start": 0,
            "end": 0,
            "confidence": 0
          }
        ]
      }
    ]
  }
}

Meet Developers Who Rely on Deepgram

I’m really impressed by the API’s ease of use and the speed of the transcription. I’ve been looking for a product to do mass-transcription of some podcasts for a while, and this is the first one I’ve found that is actually useful.

Chris Finke, Senior Engineer at Union Pacific Railroad

Deepgram is insanely easy to use. I was extremely impressed with the simplicity of the system. No unnecessary options which allowed us to implement our integration in 1 day.”

Lead Engineer, Spot Meetings

This is really our first use case with Deepgram. It’s definitely been the best out of the box transcription accuracy I’ve seen and I’ve had to utilise a number of other solutions when working with our clients. Also, it’s been great working with the team and we’re looking forward to a long term partnership with DG.”

James Iansek, Co-founder/COO, Operative Intelligence

While Deepgram offers a technically excellent product, that’s not the only reason we ultimately chose them over their competitors. We liked working with their team. The team is extremely knowledgeable about the product and their customer service is unmatched. Other providers in the space offer nothing similar.”

Software Engineer, Podsights

Incredible customer support really sets them apart from any of the others. Direct access to engineers who know the product extremely well.”

Ryan Stomel, CEO, Call Criteria

View More Stories

Not All Speech-to-Text APIs Are the Same

Behind our easy to use speech recognition API is a deep neural network that converts audio to text accurately and reliably, at insane speed and scale. Don’t believe us? Try for yourself.

Insanely Fast
Insanely Fast

Transcribe a backlog of pre-recorded audio files at up to 120X normal audio speed; i.e. transcribe one hour of audio in 30 seconds.

5 Minutes to
5 Minutes to “Hello World.”

Copy the code and get your first transcript in 10 minutes or less, including signing up for your free API key.

Super-duper Reliable
Super-duper Reliable

Transcriptions up to 90%+ accuracy with trained models and no compromise of speed.

The Features You Need to Build Amazing Experiences

Transcription

Accurate transcriptions up to 90%+ accuracy with trained models.

Real-time streaming (300-millisecond latency)

Keep the conversation flowing. Transcribe phone and meeting conversations as they happen.

Batch transcription (up to 120x speedup)

Transcribe the backlog of audio files at up to 120X normal audio speed; i.e. transcribe one hour of audio in 30 seconds. 

Multi-language

Accurately identify and transcribe audio across multiple languages, accents and dialects.

Punctuation and Capitalization

Use punctuation in your transcripts to make them easier for humans, and machines to read.

Audio Timestamps

Each word includes an associated timestamp. Drill into audio snippets with specific start and end times.

Diarization

Identify up to 10 different speakers at one time. Don’t worry we won’t charge you multiple times.

Confidence %

Each word and entire transcript is rated on confidence that the word or transcript is correct.

Deep search by phonetics

Accurately identify top terms or phrases in your audio with acoustic pattern matching, instead of text search.

REST API integration

Connect to any audio data source and deliver accurate transcripts to the user-facing system of your choice with our integrations.

Keyword boosting

Boost industry terms, unique product names, and company names to increase transcription confidence.

Redaction

Automatically redact sensitive data such as private health information or credit card information from transcripts.

Profanity filtering

Filter any profanity words from transcripts.

Multi-channel support

Reliably identify speaker changes across single and multi-channel audio.

Multi-audio types

Support over 40 different audio formats including WAV, MP3, FLAC, and AAC. No need to create different jobs for different file extensions.

Customizable

Each model is tuned to the audio you care about. This is done through state-of-the- art data labeling and model training.

Apply Now

Receive up to $100,000 to use over 12 months.

Become a Partner

When you become a partner you’re in good company.

Talk to Customer Success