Deepgram Realtime

deepgram/realtime

A provider bundle: Deepgram's Voice Agent API set to Nova-3 for listening, OpenAI GPT-4o mini for reasoning and the Aura-2 Thalia English voice. One WebSocket handles turn-taking, barge-in and function calls; the API reached general availability in June 2025.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/audio/speech-to-speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepgram/realtime",
  "input_audio": {
    "data": "BASE64_AUDIO",
    "format": "pcm16",
    "sample_rate": 24000,
    "channels": 1
  },
  "output_audio": {
    "format": "pcm16",
    "sample_rate": 24000
  }
}'

Input Price: $0.0638 / minute
Output Price: —
Input: Audio
Output: Audio

Capabilities

Explore what Deepgram Realtime supports, then use the API section for a request tailored to this model.

BatchRealtimeDuplexAudio inputAudio outputTools

Languages

English

Model Information

Provider: Deepgram
Product: Conversational
Release Date: Jun 16, 2025
Data Policy: Configurable
Region: Unknown
Input: Audio
Output: Audio

Provider Documentation

Playground

Try Deepgram Realtime by Deepgram. Requests use the selected workspace’s credits and API pricing.

Deepgram Realtime

This model uses a dedicated input format. Explore its API example or open the supported playground.

Open playground

Providers

Compare available endpoints, pricing, and context limits for Deepgram Realtime.

Provider	Context	Output	Input Price	Output Price	Endpoint
Deepgram	Not specified	Audio	$0.0638 / minute	—	`deepgram/realtime:deepgram`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Input formats	pcm16, g711_ulaw, g711_alaw
Output formats	pcm16, g711_ulaw, g711_alaw
Max session seconds	3600

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/audio/speech-to-speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepgram/realtime",
  "input_audio": {
    "data": "BASE64_AUDIO",
    "format": "pcm16",
    "sample_rate": 24000,
    "channels": 1
  },
  "output_audio": {
    "format": "pcm16",
    "sample_rate": 24000
  }
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepgram/realtime` — Required model identifier.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Input formats	pcm16, g711_ulaw, g711_alaw
Output formats	pcm16, g711_ulaw, g711_alaw
Max session seconds	3600

Similar Models

Explore more conversational and compare their capabilities.

Model	Context	Input Price	Output Price
Grok Voice LatestxAI	Not specified	$0.0425 / minute	—
GPT Realtime 2.1OpenAI	Not specified	$27.20 / 1M tokens	$54.40 / 1M tokens
GPT Realtime 2.1 MiniOpenAI	Not specified	$8.50 / 1M tokens	$17.00 / 1M tokens
Gemini 3.5 Live TranslateGoogle Gemini	Not specified	$2.975 / 1M tokens	$17.85 / 1M tokens
GPT Realtime 2OpenAI	Not specified	$27.20 / 1M tokens	$54.40 / 1M tokens
Grok Voice Think Fast 1.0xAI	Not specified	$0.0425 / minute	—

View All Conversational