🚀 Meet Flux - speech recognition for real-time voice agents

Try it Now

Voice AI APIs that just work

Build with the most accurate, realistic, and cost-effective APIs for speech-to-text, text-to-speech, and voice agents. Trusted by 200,000+ AI builders and leading enterprises. Available in real-time and batch, cloud and self-hosted.

Sign Up Free Playground

Speech to Text

Text to Speech

Voice Agent

Audio Intelligence

Flux: Voice Agents

Nova: Transcription

Speak

Flux: Voice Agents

Speak

Nova: Transcription

Speak

English

​

OR

Use your own file

Your transcriptions will show here.

Copy

Download

Trusted by the world’s top Enterprises and Startups

A single, unified Voice Agent 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.

User

Your customer or end user speaking naturally.

Audio input

Partner-provided transport layer that bridges stream audio into Deepgram's APIs and plays back TTS audio to the end user, including Telephony partners (via PSTN/SIP)

Speech to Text (STT)

Conversational speech recognition that detects end-of-turn and interruptions, and streams transcripts in real-time.

LLM orchestration

Coordinates context, memory, and AI reasoning.

• Context: Maintains conversation history and system settings.

• System Updates: Adjusts role or behavior.

• Prompt Updates: Refines instructions in real time.

• Response Injections: Adds guidance or context.

• Function Calling: Executes actions or fetches data.

• LLM (via API): Connects to language models for response generation.

Text to Speech (TTS)

Converts AI responses into natural-sounding speech.

Business logic

Your custom application logic. Executes domain-specific actions, integrates external APIs, or adds validation before results flow back into the agent.

External systems

Databases, APIs, and back-office systems that the agent interacts with. Results are fed back into the conversation context for grounding.

Try it now

Choose your Voice AI journey

Choose the path that best fits your business needs and technical requirements.

Build with APIs

Voice AI Infrastructure for Builders.

For developers and product teams ready to move fast with flexible APIs.

Start Building

Integrate Deepgram

Voice AI for Platforms & Partners.

For platforms and partners embedding enterprise-grade Voice AI.

Become A Partner

Custom models

Voice AI Solutions Built with You.

For enterprises with unique workflows and compliance needs.

Talk to Sales

Solutions that scale

As the industry's voice AI leader, Deepgram drives better outcomes with enterprise solutions that deliver intelligent voice experiences safely, securely, and at scale.

View Enterprise Solutions

Trusted by startups and enterprises

Discover the power of our product through real stories.

I’d recommend Deepgram to any B2B SaaS company that’s looking for the best-in-breed transcription and customer service and customer success.

Josh Schachter

CEO, UpdateAI

As we’ve begun to roll out Deepgram to our customers, we’ve noticed the platform’s distinct ability to quickly and accurately transcribe product and company names.

Adam Larsen

CTO, Creovai

I have not had such a nice experience working with somebody's API in so long. And Deepgram did that. And then I also realized, like, it's cheap as hell.

Wes Bos

Dev Influencer, Syntax Podcast

Not only is Deepgram’s technology the most advanced we found, but working with them has been an absolute pleasure.

Craig Akal

Co-founder/Director, Elerian AI

The quality of your transcript determines the quality of the information you can extract from its text. Having a customized speech model literally pays dividends on all natural language processing that happens downstream.

\
\
Scott Hoch\
\
Head of Data, Revenue.io

IT teams love Deepgram’s speed and accuracy, while tech teams appreciate how the platform doesn’t use the same open-source space that other vendors do, which helps with the total cost of ownership.

Pete Ellis

CPO, Red Box

I’d recommend Deepgram to any B2B SaaS company that’s looking for the best-in-breed transcription and customer service and customer success.

Josh Schachter

CEO, UpdateAI

As we’ve begun to roll out Deepgram to our customers, we’ve noticed the platform’s distinct ability to quickly and accurately transcribe product and company names.

Adam Larsen

CTO, Creovai

I have not had such a nice experience working with somebody's API in so long. And Deepgram did that. And then I also realized, like, it's cheap as hell.

Wes Bos

Dev Influencer, Syntax Podcast

Not only is Deepgram’s technology the most advanced we found, but working with them has been an absolute pleasure.

Craig Akal

Co-founder/Director, Elerian AI

The quality of your transcript determines the quality of the information you can extract from its text. Having a customized speech model literally pays dividends on all natural language processing that happens downstream.

\
\
Scott Hoch\
\
Head of Data, Revenue.io

IT teams love Deepgram’s speed and accuracy, while tech teams appreciate how the platform doesn’t use the same open-source space that other vendors do, which helps with the total cost of ownership.

Pete Ellis

CPO, Red Box

I’d recommend Deepgram to any B2B SaaS company that’s looking for the best-in-breed transcription and customer service and customer success.

Josh Schachter

CEO, UpdateAI

As we’ve begun to roll out Deepgram to our customers, we’ve noticed the platform’s distinct ability to quickly and accurately transcribe product and company names.

Adam Larsen

CTO, Creovai

I have not had such a nice experience working with somebody's API in so long. And Deepgram did that. And then I also realized, like, it's cheap as hell.

Wes Bos

Dev Influencer, Syntax Podcast

Not only is Deepgram’s technology the most advanced we found, but working with them has been an absolute pleasure.

Craig Akal

Co-founder/Director, Elerian AI

The quality of your transcript determines the quality of the information you can extract from its text. Having a customized speech model literally pays dividends on all natural language processing that happens downstream.

\
\
Scott Hoch\
\
Head of Data, Revenue.io

IT teams love Deepgram’s speed and accuracy, while tech teams appreciate how the platform doesn’t use the same open-source space that other vendors do, which helps with the total cost of ownership.

Pete Ellis

CPO, Red Box

I’d recommend Deepgram to any B2B SaaS company that’s looking for the best-in-breed transcription and customer service and customer success.

Josh Schachter

CEO, UpdateAI

As we’ve begun to roll out Deepgram to our customers, we’ve noticed the platform’s distinct ability to quickly and accurately transcribe product and company names.

Adam Larsen

CTO, Creovai

I have not had such a nice experience working with somebody's API in so long. And Deepgram did that. And then I also realized, like, it's cheap as hell.

Wes Bos

Dev Influencer, Syntax Podcast

Not only is Deepgram’s technology the most advanced we found, but working with them has been an absolute pleasure.

Craig Akal

Co-founder/Director, Elerian AI

The quality of your transcript determines the quality of the information you can extract from its text. Having a customized speech model literally pays dividends on all natural language processing that happens downstream.

\
\
Scott Hoch\
\
Head of Data, Revenue.io

IT teams love Deepgram’s speed and accuracy, while tech teams appreciate how the platform doesn’t use the same open-source space that other vendors do, which helps with the total cost of ownership.

Pete Ellis

CPO, Red Box

Unlock voice AI at scale with an API Call

Get conversational intelligence with transcription and understanding on the world's best speech AI platform.

Sign Up Free Get a Demo