Deepgram Post Listen Transcribe
From 5.16 credits/min
ae_deepgram_post_listen_transcribe
Submit prerecorded audio or video to Deepgram for background transcription. Pass the file URL as request_body.url. The submission returns an AE task_id. Use ae_get_result with that ID to retrieve the complete transcript, timestamps and metadata. Set diarize_model=v2 to include speaker labels. language=multi enables multilingual transcription. Billing uses actual audio duration.
From 5.16 credits/min
Pricing
From 5.16 credits/min
| Mode | Per minute | Per second |
|---|---|---|
| Monolingual | 5.16 credits | 0.086 credits |
| Multilingual | 6.24 credits | 0.104 credits |
Billed per second of actual audio. Speaker diarization is included.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
tag | string | array | No | Label your requests for the purpose of identification during usage reporting | — |
extra | string | array | No | Arbitrary key-value pairs that are attached to the API response for usage in downstream processing | — |
model | string | No | AI model used to process submitted audio | base-general |
redact | string | array | No | Redaction removes sensitive information from your transcripts | — |
search | string | array | No | Search for terms or phrases in submitted audio | — |
topics | boolean | No | Detect topics throughout a transcript or text | false |
intents | boolean | No | Recognizes speaker intent throughout a transcript or text | false |
keyterm | array | No | Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3 | — |
replace | string | array | No | Search for terms or phrases in submitted audio and replaces them | — |
version | string | No | Version of an AI model to use | latest |
encoding | enum (linear16 | flac | mulaw | amr-nb | amr-wb | opus | speex | g729) | No | Specify the expected encoding of your submitted audio | — |
keywords | string | array | No | Keywords can boost or suppress specialized terminology and brands | — |
language | string | No | The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available | en |
numerals | boolean | No | Numerals converts numbers from written format to numerical format | false |
dictation | boolean | No | Dictation mode for controlling formatting with dictated speech | false |
punctuate | boolean | No | Add punctuation and capitalization to the transcript | false |
sentiment | boolean | No | Recognizes the sentiment throughout a transcript or text | false |
summarize | string | boolean | No | Summarize content. For Listen API, supports string version option. For Read API, accepts boolean only. | — |
utt_split | number | No | Seconds to wait before detecting a pause between words in submitted audio | 0.8 |
paragraphs | boolean | No | Splits audio into paragraphs to improve transcript readability | false |
utterances | boolean | No | Segments speech into meaningful semantic units | false |
mip_opt_out | boolean | No | Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip | false |
custom_topic | string | array | No | Custom topics you want the model to detect within your input audio or text if present Submit up to `100`. | — |
filler_words | boolean | No | Filler Words can help transcribe interruptions in your audio, like "uh" and "um" | false |
measurements | boolean | No | Spoken measurements will be converted to their corresponding abbreviations | false |
multichannel | boolean | No | Transcribe each audio channel independently | false |
request_body | object | No | Audio file URL to transcribe | — |
request_body.url | string | Yes | No parameter description. | — |
smart_format | boolean | No | Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability | false |
custom_intent | string | array | No | Custom intents you want the model to detect within your input audio if present | — |
diarize_model | enum (latest | v1 | v2) | No | Enable speaker attribution using a model version: latest, v1, or v2. For prerecorded audio, use v2 to pin the newer model. Omit this parameter when speaker labels are unnecessary. | — |
detect_entities | boolean | No | Identifies and extracts key entities from content in submitted audio | false |
detect_language | boolean | array | No | Identifies the dominant language spoken in submitted audio | — |
profanity_filter | boolean | No | Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely | false |
custom_topic_mode | unknown | No | Sets how the model will interpret strings submitted to the `custom_topic` param. When `strict`, the model will only return topics submitted using the `custom_topic` param. When `extended`, the model will return its own detected topics in addition to those submitted using the `custom_topic` param | extended |
custom_intent_mode | unknown | No | Sets how the model will interpret intents submitted to the `custom_intent` param. When `strict`, the model will only return intents submitted using the `custom_intent` param. When `extended`, the model will return its own detected intents in the `custom_intent` param. | extended |
Invocation example
Parameter templateGenerated from the parameter configuration. Replace the sample values before use.
POST
/agent-api/v1/tool/executeX-Api-KeyRequest coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_deepgram_post_listen_transcribe' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {}
}'Response exampleresponse.json
"validating \"arguments\": validating root: required: missing properties: [\"url\"]"Guides using this tool
See how this tool fits into real workflows





