Speech-to-Text API

Deepgram

Enterprise-grade Voice AI APIs for real-time speech-to-text, text-to-speech, and conversational voice agents.

Overview

Deepgram offers advanced voice AI solutions including speech-to-text, text-to-speech, and a unified Voice Agent API that integrates conversational AI with real-time transcription and natural voice synthesis. It supports over 36 languages with ultra-low latency, high accuracy, and customizable models tailored for industries like healthcare, customer support, and media. Trusted by enterprises and startups, Deepgram enables scalable, secure, and cost-effective voice AI experiences through flexible cloud and self-hosted deployments.

Updated Oct 18, 2026

10 things

What Deepgram has

For developers

Programmatic access to the product's data and features for developers.
Run the software on your own servers instead of the vendor's cloud.
A command-line interface that lets you run the tool from a terminal or scripts.
A Model Context Protocol server that lets AI tools connect to and act on your data.
A toolkit that lets developers build on the product using their preferred programming language.

Hosting and storage

Vendor-provided online infrastructure for deploying and running software.
A dedicated cloud environment for running software and keeping its data separate.

Support

Faster answers from the support team than customers get as standard.
Get help from the support team by writing to them via email.

Extras

An online space where users can connect, share tips, and help each other.

Pros and cons

Pros

Unified API simplifies building conversational AI agents by integrating STT, TTS, and LLM orchestration.
Ultra-low latency transcription with sub-300ms delay supports real-time applications.
Supports over 36 languages and dialects for global reach.
Custom and industry-tuned models improve accuracy for specialized domains.
Flexible pricing plans including pay-as-you-go and enterprise options with self-hosting available.

Cons

Pricing can be complex due to multiple models and add-ons like redaction and keyterm prompting.
Some advanced features require contacting sales, limiting transparency for smaller users.
Text-to-speech currently supports only English language.
Voice Agent API pricing depends on WebSocket connection time, which may be harder to estimate.
Limited public documentation on detailed LLM integration options and tiers.

As of October 2026

Pricing

Enterprise
Custom
on request

Developer features

Unified voice API
Instead of stitching together separate components, Deepgram unifies speech-to-text, text-to-speech, and LLM orchestration into a single API, reducing complexity, latency, and cost.

You?

Be the first to rate Deepgram

Your review helps others make better decisions. No account needed. Takes about 10 seconds.

Featured Video

See Deepgram at work before you try it.

Watch on YouTube

0 questions

Frequently Asked Questions

Community reviews

Write a review

No written reviews yet. Be the first to share your experience.

Community reviews

Write a review

No written reviews yet. Be the first to share your experience.

10 things

What Deepgram has

For developers

Programmatic access to the product's data and features for developers.
Run the software on your own servers instead of the vendor's cloud.
A command-line interface that lets you run the tool from a terminal or scripts.
A Model Context Protocol server that lets AI tools connect to and act on your data.
A toolkit that lets developers build on the product using their preferred programming language.

Hosting and storage

Vendor-provided online infrastructure for deploying and running software.
A dedicated cloud environment for running software and keeping its data separate.

Support

Faster answers from the support team than customers get as standard.
Get help from the support team by writing to them via email.

Extras

An online space where users can connect, share tips, and help each other.

Pros and cons

Pros

Unified API simplifies building conversational AI agents by integrating STT, TTS, and LLM orchestration.
Ultra-low latency transcription with sub-300ms delay supports real-time applications.
Supports over 36 languages and dialects for global reach.
Custom and industry-tuned models improve accuracy for specialized domains.
Flexible pricing plans including pay-as-you-go and enterprise options with self-hosting available.

Cons

Pricing can be complex due to multiple models and add-ons like redaction and keyterm prompting.
Some advanced features require contacting sales, limiting transparency for smaller users.
Text-to-speech currently supports only English language.
Voice Agent API pricing depends on WebSocket connection time, which may be harder to estimate.
Limited public documentation on detailed LLM integration options and tiers.

As of October 2026

Pricing

Enterprise
Custom
on request

Developer features

Unified voice API
Instead of stitching together separate components, Deepgram unifies speech-to-text, text-to-speech, and LLM orchestration into a single API, reducing complexity, latency, and cost.

You?

Be the first to rate Deepgram

Your review helps others make better decisions. No account needed. Takes about 10 seconds.

Featured Video

See Deepgram at work before you try it.

Watch on YouTube

0 questions

Deepgram

Overview

What Deepgram has

For developers

Hosting and storage

Support

Extras

Pros and cons

Pros

Cons

Pricing

Deepgram pricing plans

Enterprise

Developer features

Unified voice API

Be the first to rate Deepgram

Featured Video

Frequently Asked Questions

What Deepgram has

For developers

Hosting and storage

Support

Extras

Pros and cons

Pros

Cons

Pricing

Deepgram pricing plans

Enterprise

Developer features

Unified voice API

Be the first to rate Deepgram

Featured Video

Frequently Asked Questions

More in Speech-to-Text API

Speechmatics

AssemblyAI

Gladia

More in Speech-to-Text API

Speechmatics

AssemblyAI

Gladia