Skip to main content
POST
/
v1
/
stt
/
slng
/
deepgram
/
nova:3-en
Nova 3 (English)
curl --request POST \
  --url https://api.slng.ai/v1/stt/slng/deepgram/nova:3-en \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form audio='@example-file' \
  --form language=en
{
  "results": {
    "channels": [
      {
        "alternatives": [
          {
            "transcript": "hello from sunny barcelona",
            "confidence": 0.98
          }
        ]
      }
    ]
  },
  "metadata": {
    "request_id": "req-123",
    "model": "nova-3"
  }
}

Authorizations

​
Authorization
string
header
required

API key issued by SLNG. Pass as Authorization: Bearer <token>.

Headers

​
X-Region-Override
enum<string>

Target region override. Auto-selected if not provided.

Available options:
eu-north-1,
ap-southeast-2

Body

SLNG-hosted Deepgram STT processing options.

​
audio
file

Audio file (multipart) or base64-encoded audio (JSON).

​
url
string

Publicly accessible audio URL.

Example:

"https://docs.slng.ai/audio/hello.wav"

​
model
string
default:nova-3

Model name override.

​
enable_partials
boolean
default:true

Enable partial/interim transcription results for streaming.

​
punctuate
boolean
default:false

Add punctuation and capitalization.

​
smart_format
boolean
default:false

Apply formatting to improve readability (dates, times, numbers, etc.).

​
utterances
boolean
default:false

Segment transcript into utterances.

​
paragraphs
boolean
default:false

Add paragraph formatting.

​
numerals
boolean
default:false

Convert spoken numbers to digits.

​
profanity_filter
boolean
default:false

Filter profanity from transcript.

​
redact
enum<string>[]

Redact sensitive information (pci, ssn, numbers).

Available options:
pci,
ssn,
numbers
​
detect_language
boolean
default:false

Auto-detect spoken language.

​
filler_words
boolean
default:false

Include filler words (uh, um) in transcript.

​
multichannel
boolean
default:false

Enable multi-channel audio processing.

​
keywords
string[]

Keywords to boost recognition accuracy.

​
encoding
enum<string>
default:linear16

Input audio encoding.

Available options:
linear16,
flac,
mulaw,
amr-nb,
amr-wb,
opus,
speex,
mp3,
mp4,
webm,
aac,
ogg
​
sample_rate
integer
default:16000

Input audio sample rate in Hz.

​
channels
integer

Number of audio channels.

Required range: x >= 1
​
endpointing
default:10

Time in milliseconds of silence before finalizing speech. Enabled by default at 10ms on Deepgram's side. Set to false to disable endpointing entirely.

Required range: x >= 0
​
utterance_end_ms
integer
default:1000

Time in milliseconds of silence between words before sending an UtteranceEnd message. Default is 1000ms, minimum 200ms, maximum 5000ms. Requires interim_results (enable_partials) to be true.

Required range: 200 <= x <= 5000
​
tag
string

Tag for request tracking.

​
language
enum<string>

Supported English language code.

Available options:
en,
en-au,
en-us,
en-nz,
en-gb,
en-in
Example:

"en"

Response

Transcription successful.

3rd Party Deepgram API response format.

​
results
object
required
​
metadata
object