Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Deepgram speech APIs - verified

Deepgram speech API pricing and models

Deepgram: 5 speech-to-text models and 3 text-to-speech models, read from the provider's own pages on October 18, 2026. Its lowest speech-to-text rate converts to $0.258 an hour (Nova-3 Monolingual). No model here has a scheduled shutdown date.

Read from deepgram.com, developers.deepgram.com. Compare every speech API

Speech-to-text
5
Text-to-speech
3
Realtime voice
0
Retiring
0

Speech-to-text

Compare every speech-to-text provider

Flux English

Speech-to-text - flux-general-en

Price (provider's unit)

$0.0077/min streaming (regular price)

“Flux English i Conversational speech recognition for real-time voice agents with built-in turn detection, natural interruption handling, and ultra-low latency. | Current price$0.0065/min ~~Regular price$0.0077/min~~”
deepgram.com

Note: Limited-time promotional streaming rate shown as 'Current price$0.0065/min' (Pay As You Go); the page gives no end date.

Converted $/hour (our arithmetic)
  • $0.462 streamingconverted from $0.0077 per minute
Languages

English

“| flux-general-en | English (all accents): en |”
developers.deepgram.com
Streaming

Yes

“Conversational speech recognition for real-time voice agents with built-in turn detection, natural interruption handling, and ultra-low latency.”
deepgram.com
Max audio
Not stated
Status
Not stated

Features

  • built-in turn detection

    “built-in turn detection, natural interruption handling”
    deepgram.com

Promo labelled 'Limited-time promotional rates on streaming.' with no end date.

Flux Multilingual

Speech-to-text - flux-general-multi

Price (provider's unit)

$0.0078/min streaming

“natural interruption handling, and ultra-low latency. | $0.0078/min | $0.0068/min |”
deepgram.com
Converted $/hour (our arithmetic)
  • $0.468 streamingconverted from $0.0078 per minute
Languages

10 languages derived

“| flux-general-multi | Multilingual (English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch): en, es, fr, de, hi, ru, pt, ja, it, nl |”
Context - developers.deepgram.com

Note: Count of the languages named on the page (10).

Streaming

Yes

“Conversational speech recognition for real-time voice agents that handle multiple languages within a single conversation”
deepgram.com
Max audio
Not stated
Status
Not stated

Nova-3 Monolingual

Speech-to-text - nova-3

Price (provider's unit)

$0.0043/min pre-recorded; $0.0077/min streaming (regular price)

“far field audio. | $0.0043/min | $0.0036/min |”
deepgram.com

Note: Quote is the Pre-Recorded table row. Streaming table row: 'Current price$0.0048/min ~~Regular price$0.0077/min~~' (limited-time promotional rate, no end date given).

Converted $/hour (our arithmetic)
  • $0.258 pre-recordedconverted from $0.0043 per minute
  • $0.462 streamingconverted from $0.0077 per minute
Languages

45+ languages (Nova models)

“Nova models support 45+ languages with advanced capabilities including Speaker Diarization (multi-speaker detection), Smart Formatting for readability, Keyterm Prompting, and Automatic Language Detection.”
deepgram.com
Streaming

Yes

“Our highest performing model. Recommended for most use cases, especially audio with multiple languages, background noise, crosstalk and far field audio. | Current price$0.0048/min ~~Regular price$0.0077/min~~”
deepgram.com
Max audio
Not stated
Status
Not stated

Features

  • speaker diarization (included pre-recorded; $0.0020/min streaming)

    “| Speaker Diarization | Detect multiple speakers and label who spoke when in the transcript. | Included | Included |”
    deepgram.com

  • keyterm prompting add-on

    “| Keyterm Prompting | Boost accuracy for specific domain-specific jargon, product names, or acronyms important to your use case. | $0.0013/min | $0.0012/min |”
    deepgram.com

The docs language list for nova-3 has 63 named language entries (our count), more than the pricing page's '45+'.

Nova-3 Multilingual

Speech-to-text - nova-3 (language=multi)

Price (provider's unit)

$0.0052/min pre-recorded; $0.0092/min streaming (regular price)

“far field audio. | $0.0052/min | $0.0043/min |”
deepgram.com

Note: Quote is the Pre-Recorded table row. Streaming table row: 'Current price$0.0058/min ~~Regular price$0.0092/min~~' (limited-time promotional rate, no end date given).

Converted $/hour (our arithmetic)
  • $0.312 pre-recordedconverted from $0.0052 per minute
  • $0.552 streamingconverted from $0.0092 per minute
Languages

10 languages with code-switching derived

“Multilingual (English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch): multi”
Context - developers.deepgram.com

Note: Count of the languages named on the page (10).

Streaming

Yes

“Our highest-accuracy multilingual model with automatic language detection.”
deepgram.com
Max audio
Not stated
Status
Not stated

Deepgram Whisper Cloud (Whisper Large)

Speech-to-text - whisper-large

Price (provider's unit)

$0.0048/min pre-recorded

“| Whisper Large | $0.0048/min | $0.0048/min |”
deepgram.com
Converted $/hour (our arithmetic)
  • $0.288 pre-recordedconverted from $0.0048 per minute
Languages
Not stated
Streaming

No

“Pre-Recorded pricing”
deepgram.com
Max audio

up to 20 minutes of processing time

“Long audio files are supported up to a maximum of 20 minutes of processing time (the maximum length of the audio depends on the size of the Whisper model).”
developers.deepgram.com
Status
Not stated

Limited to 5 concurrent requests on pay-as-you-go.

Text-to-speech

Compare every text-to-speech provider

Flux TTS

Text-to-speech - Flux TTS

Price (provider's unit)

$0.0450/1k characters

“| Flux TTS | $0.0450/1k characters | $0.0405/1k characters |”
deepgram.com
Languages
Not stated
Streaming
Not stated
Limit per request
Not stated
Status
Not stated

Matching-credit promotion through December 31, 2026.

Aura-2

Text-to-speech - aura-2

Price (provider's unit)

$0.030/1k characters

“| Aura-2 | $0.030/1k characters | $0.027/1k characters |”
deepgram.com
Languages

English, Spanish, German, French, Dutch, Italian, Japanese

“Deepgram's Aura text-to-speech supports the following languages:”
developers.deepgram.com
Streaming
Not stated
Limit per request
Not stated
Status
Not stated

The Language Support list on the voices page names English (en), Spanish (es), German (de), French (fr), Dutch (nl), Italian (it) and Japanese (ja).

Aura-1

Text-to-speech - aura-1

Price (provider's unit)

$0.0150/1k characters

“| Aura-1 | $0.0150/1k characters | $0.0135/1k characters |”
deepgram.com
Languages
Not stated
Streaming
Not stated
Limit per request
Not stated
Status
Not stated

FAQ

How much does Deepgram speech-to-text cost?

Flux English: $0.0077/min streaming (regular price). Flux Multilingual: $0.0078/min streaming. Nova-3 Monolingual: $0.0043/min pre-recorded; $0.0077/min streaming (regular price). Nova-3 Multilingual: $0.0052/min pre-recorded; $0.0092/min streaming (regular price). Deepgram Whisper Cloud (Whisper Large): $0.0048/min pre-recorded. Prices are in Deepgram's own units as of October 18, 2026.

How much does Deepgram text-to-speech cost?

Flux TTS: $0.0450/1k characters. Aura-2: $0.030/1k characters. Aura-1: $0.0150/1k characters. Prices are in Deepgram's own units as of October 18, 2026.

Sources

Verified from each provider's own pricing pages and model docs; every quote was string-matched against the page that day. Prices are shown in the provider's own unit. Values marked derived were counted by us or taken from Azure's Retail Prices API, not from a pricing page. Prices change without notice; check the linked source before you commit a budget to one.

Newsletter

Know when a speech API changes its prices

One email per week. New model releases, pricing changes and what they mean for what you build.