OpenTranscription
OpenTranscription
RankerModelsPlayground
OpenTranscription
OpenTranscription

One API to every speech-to-text model worth using. Compare them on your audio, route to the best one, pay per second.

Platform status

Product

RankerModelsTranscriptionsPlaygroundBlog

Developers

DocumentationReliabilityAPI VersioningStatus

Legal

Privacy PolicyTerms of ServiceSupport
© 2026 OpenTranscription

Catalog · 43 models · 15 providers

Transcription models.

Every speech-to-text model worth using, one rate card.

Price Range

$0.0007

$0.075

Compliance

Capabilities

Best For:

1 active

10

Total models

49

Languages

$0.0058

Cheapest /min

16.4%

Best WER

10 models

filtered from 43

Base

Deepgram

Batch
United States

Deepgram Base model — high volume, cost-effective

$0.0145/min

WER

25.04%

CER

18.09%

Speed Factor

0.1x

Uptime

100.0%

Billing

per 1s

Retention

No retention

19 languages

(view all)

Auto-detectDiarizationWord Timestamps+1
TranscribeView Benchmarks
Enhanced

Deepgram

Batch
United States

Deepgram Enhanced model — high accuracy for uncommon words

$0.0165/min

WER

24.86%

CER

14.27%

Speed Factor

0.1x

Uptime

100.0%

Billing

per 1s

Retention

No retention

15 languages

(view all)

Auto-detectDiarizationWord Timestamps+1
TranscribeView Benchmarks
Flux

Deepgram

Realtime
United States

First conversational ASR model built for voice agents — model-integrated endpointing

$0.0077/min

TTFW (P50)

289 ms

Speed Factor

0.1x

Uptime

81.8%

Billing

per 1s

Retention

No retention

1 languages

(view all)

endpointing
CS
turn detection+1
TranscribeView Benchmarks
Nova-2

Deepgram

Batch & Realtime
United States

Deepgram's Nova-2 speech recognition

$0.0058/min
Fastest

WER

16.54%

CER

11.93%

Speed Factor

0.1x

Uptime

83.3%

Billing

per 1s

Retention

No retention

33 languages

(view all)

Auto-detectDiarization
CS
+2
TranscribeView Benchmarks
Nova-2 Conversational AI

Deepgram

Batch & Realtime
United States

Optimized for human-to-bot interactions (IVR, voice assistants)

$0.0058/min

WER

18.23%

CER

13.27%

Speed Factor

0.1x

Billing

per 1s

Retention

No retention

1 languages

(view all)

Diarization
CS
Word Timestamps+1
TranscribeView Benchmarks
Nova-2 Finance

Deepgram

Batch & Realtime
Deprecated
United States

Optimized for earnings calls with finance vocabulary

$0.0058/min

WER

18.92%

CER

13.09%

Speed Factor

0.1x

Billing

per 1s

Retention

No retention

1 languages

(view all)

Diarization
CS
Word Timestamps+1
TranscribeView Benchmarks
Nova-2 Meeting

Deepgram

Batch & Realtime
United States

Optimized for conference room audio

$0.0058/min

WER

16.74%

CER

11.73%

Speed Factor

0.1x

Billing

per 1s

Retention

No retention

1 languages

(view all)

Diarization
CS
Word Timestamps+1
TranscribeView Benchmarks
Nova-2 Phone Call

Deepgram

Batch & Realtime
United States

Optimized for low-bandwidth phone call audio

$0.0058/min

WER

16.38%

CER

12.42%

Speed Factor

0.1x

Billing

per 1s

Retention

No retention

1 languages

(view all)

Diarization
CS
Word Timestamps+1
TranscribeView Benchmarks
Nova-2 Voicemail

Deepgram

Batch & Realtime
United States

Optimized for low-bandwidth single speaker voicemail

$0.0058/min

WER

17.51%

CER

12.36%

Speed Factor

0.1x

Billing

per 1s

Retention

No retention

1 languages

(view all)

CS
Word TimestampsCustom Vocabulary
TranscribeView Benchmarks
Nova-3

Deepgram

Batch & Realtime
United States

Deepgram's flagship model — 53% lower WER vs competitors, code-switching support

$0.0077/min
Best Noisy
Best Technical

WER

20.98%

CER

11.48%

Speed Factor

0.1x

Uptime

50.0%

Billing

per 1s

Retention

No retention

47 languages

(view all)

Auto-detectDiarizationSmart Format+3
TranscribeView Benchmarks

All model comparisons

Every head-to-head we index, grouped by model.

Chirp 3

vs Voxtral Mini Transcribevs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Nova-3

vs Chirp 3vs Voxtral Mini Transcribevs Gladia Solaria-3vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Scribe v2vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Gladia Solaria-3

vs Chirp 3vs Voxtral Mini Transcribevs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Amazon Transcribe

vs Chirp 3vs Voxtral Mini Transcribevs Nova-3vs Gladia Solaria-3vs Nova-2vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Scribe v2vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Nova-2

vs Chirp 3vs Voxtral Mini Transcribevs Nova-3vs Gladia Solaria-3vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Scribe v2vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Scribe v2

vs Chirp 3vs Voxtral Mini Transcribevs Gladia Solaria-3vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Qwen3 ASR Flash

vs Chirp 3vs Voxtral Mini Transcribevs Nova-3vs Gladia Solaria-3vs Amazon Transcribevs Nova-2vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Scribe v2vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs Whisper Large V3 (Groq)vs GPT-4o Transcribe Diarizevs Speechmatics Standard

Voxtral Mini Transcribe

vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs GPT-4o Transcribe Diarizevs Speechmatics Standard

Whisper Large V3 Turbo

vs Voxtral Mini Transcribevs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs GPT-4o Transcribe Diarizevs Speechmatics Standard

Whisper Large V3 (Groq)

vs Voxtral Mini Transcribevs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Mini Transcribevs Whisper Large V3 Turbovs GPT-4o Transcribe Diarizevs Speechmatics Standard

Whisper Large V3 (OpenAI)

vs Soniox STT (Async)vs Speechmatics Enhancedvs Speechmatics Standard

GPT-4o Mini Transcribe

vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs GPT-4o Transcribe Diarizevs Speechmatics Standard

GPT-4o Transcribe Diarize

vs Whisper Large V3 (OpenAI)vs Soniox STT (Async)vs Speechmatics Enhancedvs Speechmatics Standard

Soniox STT (Async)

vs Speechmatics Enhancedvs Speechmatics Standard

Speechmatics Enhanced

vs Speechmatics Standard

From the blog

Deep dives on speech-to-text accuracy, latency and pricing.

All posts
Amazon Transcribe Medical: what AWS actually ships, and what it won't tell you

What Amazon Transcribe Medical offers in 2026: features, specs, pricing vs Google and Nuance, HIPAA posture, research clues, and where it falls short.

Chirp 3: inside Google Cloud's 2025 speech stack, from HD voices to transcription

What Google Cloud Chirp 3 actually is: release timeline, WER and Elo benchmarks, pricing, specs, known issues, and how it compares to Azure and ElevenLabs.

Deepgram Base in 2026: what the legacy model still does well

Where Deepgram Base fits in 2026: API behavior, variants, latency, specs, limitations, and when to pick Nova-3 or Flux instead.