AWS Comprehend and Deepgram Integration
Demonstration of how apps are integrated in WEXTL workflow builder[4]
Connect AWS Comprehend and Deepgram to automate ai workflows. Trigger events from one app, run actions in the other and use AI to make smart decisions. Integrate apps in 3 simple steps - no code required.
- 3-day trial
- Cancel anytime
- Up to 10 minutes quick set up
- GDPR
- Data Encryption
- 2FA
- Local Data Region
Learn about AWS Comprehend and Deepgram
Detailed info you need to know about AWS Comprehend and Deepgram integrations in WEXTL. Explore which modules apps support and how you connect them.
AWS Comprehend

Amazon natural language processing service for finding insights in text.[5]
Deepgram

Speech-to-text, text-to-speech and audio intelligence for voice applications.[6]
How to connect AWS Comprehend to Deepgram
Set up your AWS Comprehend and Deepgram integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.
STEP 1
Connect AWS Comprehend and Deepgram
Save credentials in WEXTL once. We store them encrypted and reuse the authorization across every workflow[3]. No coding or API skills required.
STEP 2
Build a workflow
Paste selected AWS Comprehend and Deepgram nodes onto the canvas[4], or describe what you want and WEXTL wires the flow together with AI Builder.
STEP 3
Map your data
Choose which fields need to sync between AWS Comprehend and Deepgram. Use filters or a JS custom code step in between. Everything is on the canvas.
How does the integration between AWS Comprehend and Deepgram work in WEXTL?
WEXTL exposes actions and triggers for AWS Comprehend and Deepgram that help you connect apps and automate repetitive tasks[1]. A trigger is an event that happens, and an action is a step that performs when the event has occurred.
Deepgram triggersAWS Comprehend actions
Deepgram modules
- Watch Callback Results Starts the workflow as soon as Deepgram sends a callback result. Paste the inbound URL of this trigger into the callback address of a transcription step or Analyze Text.
- Analyze Text Runs Deepgram text analysis on pasted text or a text file. Switch on Analyze Sentiment, Detect Topics, Detect Intents or Summarize for each insight, and set Callback URL to get the result in the background.
- Create a Key Generates an API key with a Comment, Roles and optional Tags. Set Expiration Date to make the key stop working on that day, and copy the Key from the result right away.
- Create a Self-Hosted Credential Makes a credential for pulling Deepgram self-hosted images from a registry. Use Scopes to say what it may pull, which defaults to Self-hosted products, and Comment to label it.
- Create a Temporary Token Issues an access token that works for speech and text calls only. Set Lifetime (seconds) anywhere in the 1 to 3600 range, or leave it empty for 30 seconds.
- Create an Agent Configuration Saves a voice agent configuration to a Deepgram project. Add Metadata entries such as a name to store with it.
- Create an Agent Variable Defines an agent variable with a DG_NAME style name. Use Value for a number, true or false, or JSON, which is stored as that type.
- Create an Invite Invites a person by Email to a Deepgram project with the Role of Member, Admin or Owner.
- Delete a Key Removes an API key that belongs to a project.
- Delete a Project Deletes a whole Deepgram project. This cannot be undone.
- Delete a Self-Hosted Credential Deletes a credential used to pull self-hosted images.
- Delete an Agent Configuration Deletes a saved voice agent configuration.
- Delete an Agent Variable Removes a variable used by voice agents.
- Delete an Invite Cancels an invitation sent to a project.
- Generate Flux Speech Turns Text into audio with a Flux Voice such as flux-alexis-en. Use Expressivity for a calmer or livelier delivery, and write {pause:500ms} markers into the text for pauses.
- Generate Speech Converts up to 2000 characters of Text into audio with an Aura Voice. Set Speed anywhere in 0.7 to 1.5, and pick an Audio Format such as MP3 or FLAC.
- Get a Balance Reads a single balance, giving its Units and Amount.
- Get a Billing Breakdown Breaks project spending down between Start Date and End Date. Narrow it by Key, Deployment, Tag or Line Item, and use Group By to split the report.
- Get a Key Returns the Member record linked to one API key.
- Get a Model Looks up one Deepgram model: its Name, Canonical Name, Architecture, Languages and Version, and whether it supports Batch or Streaming.
- Get a Project Fetches one Deepgram project with its Project ID, Name and MIP Opt Out setting.
- Get a Project Model Reads a model within one project. Output includes the Name, Version, UUID and Formatted Output.
- Get a Request Retrieves a past request by the Request ID of a Transcribe or Speech result, or of List Requests. Output includes the Path, Response, Code and Callback.
- Get a Self-Hosted Credential Reads one self-hosted credential, giving its Member and Distribution Credentials.
- Get a Usage Breakdown Splits project usage into periods between Start Date and End Date. Use Only Requests That Used and Only Requests That Did Not Use to include or leave out requests by feature.
- Get an Agent Configuration Reads one saved voice agent configuration with its Config, Metadata and timestamps.
- Get an Agent Variable Looks up an agent variable and shows its Key, Value, Created At and Updated At.
- Get Project Usage Summarizes project usage starting at Start Date and ending at End Date, which default to the project start and today. Filter by Endpoint, Method, Deployment, Key, Model or Tag.
- Leave a Project Removes you from a Deepgram project, and you lose access to it.
- List Agent Configurations Finds voice agent configurations in a project, with Agent ID, Config and Metadata. Use Limit to cap how many are returned.
- List Agent Think Models Shows the language models an agent can think with, giving ID, Name and Provider for each.
- List Agent Variables Lists the variables that voice agents of a project use, each with a Variable ID, Key, Value and timestamps.
- List Balances Finds project balances with the Balance ID, Amount and Purchase Order ID of each.
- List Billing Fields Lists the options for billing reports over a date range, with Accessors, Deployments, Tags and Line Items in the output. Set Start Date and End Date to bound the range.
- List Invites Shows invitations sent for a project with the Email and Scope of each.
- List Keys Shows each API key in a project along with its Member.
- List Member Scopes Shows the Scopes held by a single person on a Deepgram project.
- List Members Lists project members with Member ID, Email, First Name, Last Name and Scopes.
- List Models Lists Deepgram models, speech-to-text first and then voices. Models Deepgram no longer recommends are included only on request.
- List Project Models Lists the models that belong to one project. Use Limit to set how many are shown.
- List Projects Lists your Deepgram projects, giving the Project ID and Name of each.
- List Purchases Gathers purchases recorded in a project, with Order ID, Expiration, Amount, Units and Order Type.
- List Requests Searches past requests of a project within a date range, filtered by Status, Endpoint, Method, Deployment, Key or Request ID.
- List Self-Hosted Credentials Pulls up the credentials for self-hosted installs held by a project, each with a Member and Distribution Credentials.
- List Usage Fields Lists the filterable values in usage over a date range, including Tags, Models, Processing Methods and Features.
- Make an API Call Sends a free-form request to the Deepgram REST API, signed with your saved credential.
- Remove a Member Ends the membership of a person in a Deepgram project.
- Transcribe an Audio File Transcribes an uploaded Audio File with Deepgram speech to text. Choose a Model, set Language, and enable Smart Format, Paragraphs, Detect Speakers or Redact as needed. For recordings over about 25 MB use Transcribe Audio from a URL.
- Transcribe Audio from a URL Fetches a recording from a public Audio URL and transcribes it. Deepgram downloads it itself, and audio over 10 minutes can time out, so set Callback URL for long files.
- Update a Member Scope Changes what a project member may do by applying a Role in place of the old one.
AWS Comprehend modules
- Attach a Resource Policy to a Model Attaches a JSON Policy to a custom classifier or recognizer version so another AWS account can import it. Use Policy Revision ID when replacing an existing policy, so a concurrent change is not overwritten. Output is the new Policy Revision ID.
- Batch Detect Dominant Language Finds the dominant language in each of 25 texts at most, in one request. A text needs 20 characters minimum and 5 KB maximum. Results keep the order you sent.
- Batch Detect Entities Scans up to 25 texts written in the same Language for entities. Output includes the Result List, plus an Error List for texts that failed.
- Batch Detect Key Phrases Pulls the key phrases out of several texts in one call, all sharing a single Language. Add up to 25 Texts of 5 KB each, then read Result List in the original order.
- Batch Detect Sentiment Rates the sentiment of every text in a list sharing one Language, 25 texts at most. Check the Error List for texts that could not be scored.
- Batch Detect Syntax Tags the words of several texts with their parts of speech. Syntax analysis covers English, Spanish, French, German, Italian and Portuguese, which are the choices for Language.
- Batch Detect Targeted Sentiment Judges the sentiment toward each named entity inside up to 25 texts. Targeted sentiment currently supports English only, so the Language is always English.
- Check Whether a Text Contains PII Entities Checks up to 100 KB of Text for personal information and reports which kinds appear as Labels. PII labeling supports English and Spanish, selected with Language.
- Classify a Document Sends text or a document to a trained classifier Endpoint and returns the Classes or Labels it assigns. Use either Text or Document Bytes, and Document Reader Settings to control how PDF and image content is read.
- Create a Dataset Adds a training or testing dataset to a flywheel. Use Dataset Name and Input Data to give the labeled files, and Dataset Type to say whether it trains or tests. You get the Dataset ARN.
- Create a Document Classifier Starts a custom classifier on labeled Training Data, read through the Data Access Role ARN. Use Mode to allow one class or several labels per document. You receive the Document Classifier ARN.
- Create a Flywheel Sets up a flywheel that keeps a model improving from new data. It stores datasets and statistics at the Data Lake S3 URI. Use Active Model ARN for an existing model, or Model Type and Task Settings for a new one.
- Create an Endpoint Provisions capacity for a trained model. Use Inference Units to size it, at 100 characters per second each and billed while it runs, and Model ARN or Flywheel to say what it serves.
- Create an Entity Recognizer Begins training a recognizer for your own entity types from Training Data, read with the Data Access Role ARN. Use Version Name to label this version. Output includes the Entity Recognizer ARN.
- Delete a Document Classifier Deletes a custom classifier. Only classifiers in the Trained or In Error state qualify, and not while an endpoint uses them.
- Delete a Flywheel Removes a flywheel. It cannot be deleted while an iteration is running or an endpoint relies on it.
- Delete a Resource Policy Deletes the policy attached to a custom model version, found by its Model ARN. Use Policy Revision ID to delete only when the policy is still at that revision.
- Delete an Endpoint Removes a model endpoint. A model can only be deleted after all of its endpoints are gone.
- Delete an Entity Recognizer Deletes a custom recognizer that is Trained or In Error, provided no endpoint is serving it.
- Describe a Dataset Looks up a single dataset of a flywheel and shows its Dataset Properties.
- Describe a Document Classification Job Reports how an asynchronous classification job is progressing, as Job Properties.
- Describe a Document Classifier Reads one custom classifier version and its training state from the Classifier Properties.
- Describe a Dominant Language Detection Job Looks up a language detection job that is running or finished, giving back its Job Properties.
- Describe a Flywheel Reads the configuration and status of a flywheel, summarized as Flywheel Properties.
- Describe a Flywheel Iteration Fetches the Iteration Properties of one training iteration of a flywheel, found with Flywheel and Iteration.
- Describe a Key Phrases Detection Job Pulls the Job Properties of a key phrase extraction job, whether it is still going or done.
- Describe a PII Entities Detection Job Returns Job Properties for a personal information scan, covering its progress.
- Describe a Resource Policy Reads the policy of a custom model version, found by its Model ARN. Output includes the Policy text and its Policy Revision ID.
- Describe a Sentiment Detection Job Checks on a sentiment analysis job and fetches its Job Properties.
- Describe a Targeted Sentiment Detection Job Checks on a job that scores sentiment toward named entities, giving its Job Properties.
- Describe a Topics Detection Job Gets the Job Properties of a topic modeling job that is running or finished.
- Describe an Endpoint Fetches the current state of a model endpoint, returned as Endpoint Properties.
- Describe an Entities Detection Job Retrieves the Job Properties for an entity detection run, which tell you whether it has finished.
- Describe an Entity Recognizer Returns the Recognizer Properties of one custom recognizer version.
- Describe an Events Detection Job Shows where an events detection job stands, with the Job Properties of the run.
- Detect Dominant Language Identifies the language of a text of at least 20 characters, up to 100 KB. Output lists each candidate under Languages.
- Detect Entities Finds entities in a piece of Text or in a document sent as Document Bytes. Use Language with the built-in model, or Custom Endpoint to find your own entity types.
- Detect Key Phrases Extracts the main phrases from a single text under 100 KB, written in the chosen Language. Output is a list of Key Phrases.
- Detect PII Entities Locates personal information in up to 100 KB of Text, with Language limited to English or Spanish. Output is a list of Entities.
- Detect Sentiment Scores one text of up to 5 KB, such as a message body, review or comment from an earlier step. Output includes the Sentiment and its Sentiment Score.
- Detect Syntax Tags each word of a text with its part of speech, within a 5 KB limit. Supported languages are English, Spanish, French, German, Italian and Portuguese. Syntax Tokens list the words.
- Detect Targeted Sentiment Judges sentiment toward each entity in one English text, such as a product review naming several items, with a 5 KB ceiling. Entities carry their own sentiment.
- Detect Toxic Content Scores up to 10 Text Segments for toxicity, each up to 1 KB and 10 KB in all. Toxicity detection currently works for English only, and results follow the order sent.
- Import a Model Brings a classifier or recognizer version from another account into yours, once that account has allowed it with a resource policy. Use Model Name and Version Name to label the copy, and Model KMS Key to encrypt it. Output is the Model ARN.
- List Datasets Lists the datasets of your flywheels, each as its own result with a Dataset Name, Dataset Type and Number of Documents. Use Filter to limit by status, type or creation date, and Flywheel to see one flywheel only.
- List Document Classification Jobs Shows the classification jobs you have run, naming the classifier or flywheel behind each. Use Filter on the Job Name, Job Status or submit time, one at a time.
- List Document Classifier Summaries Gives one summary per classifier name instead of per version, showing the Number of Versions and the Latest Version Status. Use Limit to cap the results of a run.
- List Document Classifiers Returns every trained or training classifier version with its Version Name, Language Code, Status and Mode. Filter by Classifier Name, Status or when it was submitted to find one.
- List Dominant Language Detection Jobs Retrieves your language detection jobs. Use Filter on Job Name or Job Status to find a particular run, and Limit to return fewer results.
- List Endpoints Lists model endpoints with their Status, Current Inference Units and Model ARN. Use Filter to show only those attached to one model, in one state, or created in a date range.
Explore alternative integrations
There are other apps[9] supported by WEXTL that can be paired with AWS Comprehend and Deepgram integrations. Pick any from the list below if the current combination isn't the one you need.
Frequently asked questions
Common questions about connecting AWS Comprehend and Deepgram.
References
List of sources used to gather information about the AWS Comprehend and Deepgram integration.
- AWS Comprehend and Deepgram integration source code, module specs and credentials implementation.
- Our AWS Comprehend and Deepgram integration documentation, structured input and output parameters, scopes, and authentication methods.
- Official vendor API documentation for AWS Comprehend and Deepgram, used to verify field meanings, authentication flows, and anything our own specs don't fully capture.
- WEXTL® visual workflow builder, anonymized data from our technical support team.
- AWS Comprehend integration information
- Deepgram integration information
- WEXTL® Scheduling
- WEXTL® Pricing and Trial
- WEXTL® Apps Library
How we write our apps documentation
Explore how WEXTL® crafted AWS Comprehend and Deepgram integration page documentation. Used sources, the role of AI, and how the team validates the result.