Deepgram Enhanced model — high accuracy for uncommon words
15 languages · benchmarked
Overall Score
61.7
#22 of 28
Word Error Rate
25.24%
Character Error Rate
15.53%
Match Error Rate
24.20%
Word Info Lost
32.56%
Avg Latency
1.9s
Benchmarks Run
31
overall WER · 28 models
Enhanced
field · 27 models
lower-left is better
8 categories
WER
lower is better
Medical
7.4%
Technical
9.8%
Legal
9.9%
Conversational
15.2%
Finance
15.4%
General
25.0%
Noisy Environment
36.4%
Code-Switching
73.3%
5 accents
pay per second
Rate
$0.0165
/min
Per-second billing. Bring your own provider key and pay your provider directly — a 5% routing fee applies (first 100 min/mo free).
Set up BYOKCost estimator
1 hour
$0.99
10 hours
$9.90
100 hours
$99
1,000 hours
$990
Billed per second of audio processed.
POST /api/v1/transcriptions
Model ID
deepgram/enhanced
Authenticate every request with your secret API key as a Bearer token. Issue a key from your dashboard.
Quickstart
Upload your audio, create a job with this model, then poll the job or set a webhook_url to be notified when it completes.
Key parameters
file_path
string
required
Storage path returned by the upload step.
model
string
required
The model to run this job on.
language
string
ISO 639-1 language code. Omit to auto-detect.
diarization
boolean
Label speakers (A, B, …) in the output.
webhook_url
string
HTTPS URL notified with the result when the job completes. Delivered events are signed (X-OT-Signature).
Response
A completed job returns the transcript in the OpenTranscription Unified Schema (OTUS).
Webhooks — skip polling
We POST a signed event to your webhook_url when a job completes or fails; verify the X-OT-Signature (HMAC-SHA256, reject if older than 300 s) and dedupe on the event id, then fetch the full transcript via GET /api/v1/transcriptions/{id}.
Rate-limited per tier — see the X-RateLimit-* response headers.
Full API referenceSupported Languages
Supported Formats
Features
Enhanced is a speech-to-text model from Deepgram. In our standardized benchmarks it reaches 25.24% word error rate, ranking #22 of 28 models tested. It supports 15 languages and runs at $0.017/min — a premium option.
Its nearest benchmarked alternative is Amazon Transcribe. Best suited for multi-speaker conversations.