Amberscript and Moonshot Integration
Demonstration of how apps are integrated in WEXTL workflow builder[4]
Keep Amberscript and Moonshot matched by integrating their events and actions. When ai events happen in Amberscript, update the Moonshot automatically - without any line of code in visual workflow builder.
- 3-day trial
- Cancel anytime
- Up to 10 minutes quick set up
- GDPR
- Data Encryption
- 2FA
- Local Data Region
Learn about Amberscript and Moonshot
Detailed info you need to know about Amberscript and Moonshot integrations in WEXTL. Explore which modules apps support and how you connect them.
Amberscript

Automated and human-verified subtitles and transcripts across 39 languages.[5]
Moonshot

Kimi models and the Hosted Agents platform from Moonshot AI.[6]
How to connect Amberscript to Moonshot
Set up your Amberscript and Moonshot integration in 3 simple steps[2]. No coding required. Up to 10 minutes setup.
STEP 1
Connect Amberscript and Moonshot
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 Amberscript and Moonshot 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 Amberscript and Moonshot. Use filters or a JS custom code step in between. Everything is on the canvas.
How does the integration between Amberscript and Moonshot work in WEXTL?
WEXTL exposes actions and triggers for Amberscript and Moonshot 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.
Amberscript triggersMoonshot actions
Amberscript modules
- Delete a Job Deletes a transcription job from your Amberscript account.
- Export to JSON Gets a job transcription as structured JSON, with its Filename, Speakers, Segments and Highlights.
- Export to SRT Builds SRT subtitles from the transcription of a job. Set Max Characters Per Row and Max Number Of Rows to limit the size of each subtitle.
- Export to Text Exports a transcription as plain text. Turn on Include Timestamps or Include Speakers to add them, and Highlights Only to leave out everything else.
- Export to VTT Turns the transcript of a job into VTT subtitles. Use Max Characters Per Row, Max Number Of Rows and Max Screen Time Per Row Seconds to shape how the lines are cut.
- Get a Transcription Status Looks up the Job status of one transcription by its Job ID.
- Make an API Call Sends a free-form request to the Amberscript REST API, signed with your saved credential.
- Request Translated Subtitles Orders translated subtitles for an existing job into a Target Language. Use Callback URL to give your own URL for the callback, and Notes to attach job notes.
- Search Jobs Finds jobs by Job Type, Status or Transcription Type, each with its Created, Language, Filename and Nr audio seconds. Use Job ID to look up one particular job.
- Upload a File Sends a File from your workflow to be transcribed. Use Callback URL to be notified when it completes, and Turnaround Time for the Perfect job type.
- Upload a File from a URL Creates a transcription job from the audio or video at a Source URL. Use Glossary ID to apply a glossary and Transcription Style for Clean Read or Verbatim. The new job reports its Job status.
- Watch Jobs Polls for jobs in one Status, Open, Error or Done, and runs once for each. Use Limit to bound the jobs handled per cycle.
Moonshot modules
- Archive a Credential Marks a credential held in a vault as archived, with its secret values erased in the process.
- Archive a Memory Store Marks a memory store as archived, and its name stays reserved.
- Archive a Session Archives an agent session, and any work in progress inside it is cancelled.
- Archive a Skill Moves a custom skill to the archive, which frees its name for a new skill.
- Archive a Thread Marks one thread of a session as archived.
- Archive a Trigger Puts a trigger in the archive. Platform-managed triggers, such as dream policy schedules, cannot be archived.
- Archive a Vault Archives a credential vault along with its active credentials.
- Archive an Agent Archives an agent. New sessions can no longer start with it, while existing sessions keep running.
- Archive an Environment Marks an environment as archived, which is final. Existing sessions are not affected, but no new session can use it.
- Cancel a Batch Cancels a batch job. Requests that already finished keep their results.
- Check Credential Coverage Looks through your vaults for a credential matching each of 1 to 50 MCP Server URLs. Use Vaults to search only up to 16 of them instead of every vault you can see.
- Create a Batch Starts a batch job that runs every chat request in an uploaded JSONL Input File. Use Completion Window for the time Moonshot has to finish it, from 12h up, and Metadata to tag it with up to 16 key-value pairs.
- Create a Chat Completion Gets a reply from a Kimi Model for a series of Messages. Use Max Completion Tokens for the longest reply and Response Format to switch between text and JSON.
- Create a Credential Saves a credential to a vault, working either as MCP server access or as an environment variable inside the sandbox. Add a Display Name such as GitHub MCP access to recognise it later.
- Create a Memory Adds a file to a memory store under a relative Path. Leave Content empty to create an empty file, or add text up to 20 MiB.
- Create a Memory Store Sets up a store whose files sessions mount as a folder. Give it a unique Name for the folder, and add a Description so the model knows what it holds.
- Create a Message Gets a Kimi answer using the Anthropic-compatible Messages API. Use Max Tokens to bound the reply, and System, Tools and Stop Sequences to steer it.
- Create a Model Response Generates a response from a plain-text Input or a whole conversation, running the kimi-k3 Model. Use Instructions for a system prompt and Max Output Tokens to bound the length.
- Create a Session Starts an agent session for an Agent in an Environment that is active and has a finished build. Use Resources to attach files, vaults and memory stores, Agent Version to pin an exact version, and Title for a readable name.
- Create a Session Event Sends a user message to a session, or interrupts the turn that is running. Use Delivery to queue the message for the next turn or steer the running one, and the output is the Queued Event ID.
- Create a Session Resource Adds a File that you uploaded to a session that is already running, and places it under upload/ in the workspace. Vaults and memory stores are attached when the session is created.
- Create a Skill Builds a custom skill from an archive that contains exactly one SKILL.md. The output has the Skill and its First Version.
- Create a Trigger Sets up recurring runs of an Agent in an Environment on a cron schedule. Use Session Mode to start fresh sessions or continue one, and Opening Messages to give each run its task.
- Create a Trigger Run Runs a trigger right now, outside its schedule. Paused and platform-managed triggers can still be run by hand. Add a Message to send text into the session as a user message.
- Create a Vault Creates a vault for the credentials that agent sessions use, under a readable Display Name. Use Metadata to tag it with up to 16 key-value pairs.
- Create an Agent Creates a hosted agent that runs on a chosen Model under a Name. Add a System Prompt for its instructions, a Description or Toolsets, and use Reasoning Effort or Model Provider to adjust the model.
- Create an Environment Creates a sandbox for agent sessions from a Name. Use Network Access and Allowed Hosts to control outbound traffic, and list pip, npm, apt or Go packages for the sandbox.
- Create an OAuth Session Prepares an OAuth authorization for an MCP Server URL in a vault, and returns an Authorize URL. Leave Credential Name empty to use the server URL as the name.
- Create Credentials Batch Stores between 1 and 20 credentials in a vault in a single call, created in the order of the Credentials list.
- Delete a Credential Removes one credential out of a vault. The deletion cannot be reversed.
- Delete a File Deletes a file you uploaded. This cannot be undone.
- Delete a Memory Removes a file from a memory store.
- Delete a Memory Store Deletes a memory store with all of its files. This cannot be undone.
- Delete a Pending Event Withdraws a queued input that an agent session has not processed yet.
- Delete a Session Removes an agent session. This cannot be undone.
- Delete a Session Resource Detaches one attachment, whether a file, a vault or a memory store, from a session.
- Delete a Skill Removes a custom skill by archiving it, which frees its name for a new skill.
- Delete a Vault Deletes a credential vault together with all its credentials.
- Delete an Artifact Deletes an artifact together with every version of it. This cannot be undone.
- Delete an Environment Removes an environment. This cannot be undone.
- Delete Memory Version Text Removes the stored text of one earlier version of a memory file. This is final.
- Estimate a Token Count Estimates the token usage of a conversation with the tokenizer of the chosen Model. The output is the Estimate.
- Fetch a Web Page Pulls the page behind an http or https Page URL and returns the Title with the page text as Markdown.
- Get a Batch Checks the Status of a batch job along with its Output File ID and Error File ID.
- Get a Credential Reads a credential stored in a vault, showing its Display Name and Authentication details.
- Get a Dream Policy Looks up the automatic maintenance policy of a memory store, with its Activity Condition and Schedule Condition.
- Get a File Reads the File Name, Size (Bytes) and Purpose of an uploaded file, with the Status of its processing.
- Get a Memory Pulls a file out of a memory store, including its Content (Base64), Path and Content Size (Bytes).
- Get a Memory Store Reads a memory store, showing its Name, Description and when it was created or updated.
- Get a Memory Version Looks up an earlier state of a memory file, giving its Operation, Source and Revision.
Explore alternative integrations
There are other apps[9] supported by WEXTL that can be paired with Amberscript and Moonshot integrations. Pick any from the list below if the current combination isn't the one you need.
Frequently asked questions
Common questions about connecting Amberscript and Moonshot.
References
List of sources used to gather information about the Amberscript and Moonshot integration.
- Amberscript and Moonshot integration source code, module specs and credentials implementation.
- Our Amberscript and Moonshot integration documentation, structured input and output parameters, scopes, and authentication methods.
- Official vendor API documentation for Amberscript and Moonshot, 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.
- Amberscript integration information
- Moonshot integration information
- WEXTL® Scheduling
- WEXTL® Pricing and Trial
- WEXTL® Apps Library
How we write our apps documentation
Explore how WEXTL® crafted Amberscript and Moonshot integration page documentation. Used sources, the role of AI, and how the team validates the result.