# Voiceflow integration

> Build, run, publish and measure Voiceflow AI agents: playbooks, functions, tools, knowledge base, conversations, transcripts, environments, tests and analytics.

- Authentication: apiKey

## Tools (171)

- **Clone environment**: Copies an environment into a new one under an alias you choose, giving somewhere to change the agent without touching the environment being cloned.
- **Compile environment**: Rebuilds the environment’s runtime form from its current definition, which is what a conversation actually executes against.
- **Connect integration**: Stores the credentials for one `api-key` integration on the project, in the shape that integration expects; `oauth` and `app` integrations connect through the Voiceflow UI instead. The response carries only a confirmation message, so refetch the integration list to see the connection.
- **Create API tool**: Adds a API tool to the environment, a saved HTTP request an agent can make. The response carries the ID that later calls address it by.
- **Create check**: Adds a test check to its turn, one assertion about an agent turn, comparing the reply or the behaviour behind it. The response carries the ID that later calls address it by.
- **Create evaluation**: Adds a evaluation to the project, a criterion a model scores past conversations against. The response carries the ID that later calls address it by.
- **Create function**: Adds a function to the environment, custom JavaScript that runs in Voiceflow’s sandbox and returns through a named path. The response carries the ID that later calls address it by.
- **Create many API tools**: Adds several API tools to the environment in one request, each taking the fields the single-create call takes. The response carries the created API tools in the same shape the list call returns.
- **Create many checks**: Adds several test checks to its turn in one request, each taking the fields the single-create call takes. The response carries the created test checks in the same shape the list call returns.
- **Create many functions**: Adds several functions to the environment in one request, each taking the fields the single-create call takes. The response carries the created functions in the same shape the list call returns.
- **Create many paths**: Adds several function paths to its function in one request, each taking the fields the single-create call takes. The response carries the created function paths in the same shape the list call returns.
- **Create many playbooks**: Adds several playbooks to the environment in one request, each taking the fields the single-create call takes. The response carries the created playbooks in the same shape the list call returns.
- **Create many runs**: Adds several test runs to the environment in one request, each taking the fields the single-create call takes. The response carries the created test runs in the same shape the list call returns.
- **Create many tests**: Adds several tests to the environment in one request, each taking the fields the single-create call takes. The response carries the created tests in the same shape the list call returns.
- **Create many tools**: Adds several tools to the environment in one request, each taking the fields the single-create call takes. The response carries the created tools in the same shape the list call returns.
- **Create many turns**: Adds several test turns to its test in one request, each taking the fields the single-create call takes. The response carries the created test turns in the same shape the list call returns.
- **Create many variables (API Tool Variable)**: Adds several API tool variables to its API tool in one request, each taking the fields the single-create call takes. The response carries the created API tool variables in the same shape the list call returns.
- **Create many variables (Function Variable)**: Adds several function variables to its function in one request, each taking the fields the single-create call takes. The response carries the created function variables in the same shape the list call returns.
- **Create many variables (Variable)**: Adds several variables to the project in one request, each taking the fields the single-create call takes. The response carries the created variables in the same shape the list call returns.
- **Create MCP server**: Adds a MCP server to the environment, a registered Model Context Protocol server whose tools an agent can call. The response carries the ID that later calls address it by.
- **Create path**: Adds a function path to its function, one of the named exits a function can return through. The response carries the ID that later calls address it by.
- **Create playbook**: Adds a playbook to the environment, a set of instructions that drives an agent toward a goal, calling tools as it needs them. The response carries the ID that later calls address it by.
- **Create project**: Adds a project to the workspace, the container that owns exactly one agent. The response carries the ID that later calls address it by.
- **Create property**: Adds a transcript property to the project, a label you define once and then set on individual conversations. The response carries the ID that later calls address it by.
- **Create run**: Adds a test run to the environment, one execution of a test, carrying how many of its checks passed. The response carries the ID that later calls address it by.
- **Create secret**: Creates a secret on the project, optionally with its value, which is written to the `main` environment's published version and never read back. Omit the value to create a placeholder for a teammate to fill in the Voiceflow UI; MCP clients must create it empty.
- **Create table document**: Adds a document to the knowledge base, a source the knowledge base retrieves from. The response carries the ID that later calls address it by.
- **Create test**: Adds a test to the environment, a scripted conversation replayed against the agent. The response carries the ID that later calls address it by.
- **Create text document**: Adds a document to the knowledge base, a source the knowledge base retrieves from. The response carries the ID that later calls address it by.
- **Create tool**: Adds a tool to the environment, something a playbook can call during a conversation. The response carries the ID that later calls address it by.
- **Create turn**: Adds a test turn to its test, one side of a scripted conversation, either what the user says or the agent reply the checks assert on. The response carries the ID that later calls address it by.
- **Create URL document**: Adds a document to the knowledge base, a source the knowledge base retrieves from. The response carries the ID that later calls address it by.
- **Create variable (API Tool Variable)**: Adds a API tool variable to its API tool, an input an API tool substitutes into its request. The response carries the ID that later calls address it by.
- **Create variable (Function Variable)**: Adds a function variable to its function, an input or output a function declares. The response carries the ID that later calls address it by.
- **Create variable (Variable)**: Adds a variable to the project, a named slot of project state an agent can read and write. The response carries the ID that later calls address it by.
- **Create workspace**: Adds a workspace to the account, the container that groups projects and the people who work on them. The response carries the ID that later calls address it by.
- **Delete API tool**: Deletes a single API tool by ID. An API tool is a saved HTTP request an agent can make. The response carries only a confirmation message, so refetch the API tools to see what is left.
- **Delete check**: Deletes a single test check by ID. A test check is one assertion about an agent turn, comparing the reply or the behaviour behind it. The response carries only a confirmation message, so refetch the test checks to see what is left.
- **Delete document**: Deletes a single document by ID. A document is a source the knowledge base retrieves from. The response carries only a confirmation message, so refetch the documents to see what is left.
- **Delete environment**: Deletes a single environment by ID. An environment is one draft-and-published copy of the agent. The response carries only a confirmation message, so refetch the environments to see what is left.
- **Delete evaluation**: Deletes a single evaluation by ID. An evaluation is a criterion a model scores past conversations against. The response carries only a confirmation message, so refetch the evaluations to see what is left.
- **Delete function**: Deletes a single function by ID. A function is custom JavaScript that runs in Voiceflow’s sandbox and returns through a named path. The response carries only a confirmation message, so refetch the functions to see what is left.
- **Delete MCP server**: Deletes a single MCP server by ID. A MCP server is a registered Model Context Protocol server whose tools an agent can call. The response carries only a confirmation message, so refetch the MCP servers to see what is left.
- **Delete path**: Deletes a single function path by ID. A function path is one of the named exits a function can return through. The response carries only a confirmation message, so refetch the function paths to see what is left.
- **Delete playbook**: Deletes a single playbook by ID. A playbook is a set of instructions that drives an agent toward a goal, calling tools as it needs them. The response carries only a confirmation message, so refetch the playbooks to see what is left.
- **Delete project**: Deletes a single project by ID. A project is the container that owns exactly one agent. The response carries only a confirmation message, so refetch the projects to see what is left.
- **Delete property**: Deletes a single transcript property by ID. A transcript property is a label you define once and then set on individual conversations. The response carries only a confirmation message, so refetch the transcript properties to see what is left.
- **Delete secret**: Deletes a secret by ID, taking every environment's values for it with it. The response carries only a confirmation message, so refetch the secret list to see what is left.
- **Delete state**: Discards the stored state for one conversation, so the next turn on that `userID` begins from the start. The response carries only a confirmation message.
- **Delete test**: Deletes a single test by ID. A test is a scripted conversation replayed against the agent. The response carries only a confirmation message, so refetch the tests to see what is left.
- **Delete tool**: Deletes a single tool by ID. A tool is something a playbook can call during a conversation. The response carries only a confirmation message, so refetch the tools to see what is left.
- **Delete turn**: Deletes a single test turn by ID. A test turn is one side of a scripted conversation, either what the user says or the agent reply the checks assert on. The response carries only a confirmation message, so refetch the test turns to see what is left.
- **Delete variable (API Tool Variable)**: Deletes a single API tool variable by ID. An API tool variable is an input an API tool substitutes into its request. The response carries only a confirmation message, so refetch the API tool variables to see what is left.
- **Delete variable (Function Variable)**: Deletes a single function variable by ID. A function variable is an input or output a function declares. The response carries only a confirmation message, so refetch the function variables to see what is left.
- **Delete variable (Variable)**: Deletes a single variable by ID. A variable is a named slot of project state an agent can read and write. The response carries only a confirmation message, so refetch the variables to see what is left.
- **Delete workspace**: Deletes a single workspace by ID. A workspace is the container that groups projects and the people who work on them. The response carries only a confirmation message, so refetch the workspaces to see what is left.
- **Disconnect integration**: Clears the stored credentials for one integration on the project, every slot it owns. The response carries only a confirmation message, so refetch the integration list to see it disconnected.
- **Export environment**: Serialises the whole environment - its agent, playbooks, tools and knowledge base - into a single document you can archive or move to another project.
- **Get agent**: Returns the environment’s agent: the global prompt, the instructions that route a turn, and the settings wrapping both.
- **Get API tool**: Returns a single API tool by ID, with the fields that define it. An API tool is a saved HTTP request an agent can make.
- **Get check**: Returns a single test check by ID, with the fields that define it. A test check is one assertion about an agent turn, comparing the reply or the behaviour behind it.
- **Get document**: Returns a single document by ID, with the fields that define it. A document is a source the knowledge base retrieves from.
- **Get environment**: Returns a single environment by ID, with the fields that define it. An environment is one draft-and-published copy of the agent.
- **Get evaluation**: Returns a single evaluation by ID, with the fields that define it. An evaluation is a criterion a model scores past conversations against.
- **Get function**: Returns a single function by ID, with the fields that define it. A function is custom JavaScript that runs in Voiceflow’s sandbox and returns through a named path.
- **Get MCP server**: Returns a single MCP server by ID, with the fields that define it. A MCP server is a registered Model Context Protocol server whose tools an agent can call.
- **Get MCP tool**: Returns a single MCP tool by ID, with the fields that define it. A MCP tool is a tool an MCP server advertises, populated by syncing the server rather than by hand.
- **Get path**: Returns a single function path by ID, with the fields that define it. A function path is one of the named exits a function can return through.
- **Get playbook**: Returns a single playbook by ID, with the fields that define it. A playbook is a set of instructions that drives an agent toward a goal, calling tools as it needs them.
- **Get project**: Returns a single project by ID, with the fields that define it. A project is the container that owns exactly one agent.
- **Get property**: Returns a single transcript property by ID, with the fields that define it. A transcript property is a label you define once and then set on individual conversations.
- **Get run**: Returns a single test run by ID, with the fields that define it. A test run is one execution of a test, carrying how many of its checks passed.
- **Get state**: Returns the stored state for one conversation - where it stands and what its variables hold - addressed by the same `userID` used to run it.
- **Get test**: Returns a single test by ID, with the fields that define it. A test is a scripted conversation replayed against the agent.
- **Get tool**: Returns a single tool by ID, with the fields that define it. A tool is something a playbook can call during a conversation.
- **Get transcript**: Returns one recorded conversation, including the turns exchanged and the traces behind them. Set `filterConversation` to keep only `text`, `speak`, and `live-agent-handoff` traces, plus any types listed in `customTraceTypes`.
- **Get turn**: Returns a single test turn by ID, with the fields that define it. A test turn is one side of a scripted conversation, either what the user says or the agent reply the checks assert on.
- **Get variable (API Tool Variable)**: Returns a single API tool variable by ID, with the fields that define it. An API tool variable is an input an API tool substitutes into its request.
- **Get variable (Function Variable)**: Returns a single function variable by ID, with the fields that define it. A function variable is an input or output a function declares.
- **Get variable (Variable)**: Returns a single variable by ID, with the fields that define it. A variable is a named slot of project state an agent can read and write.
- **Get workspace**: Returns a single workspace by ID, with the fields that define it. A workspace is the container that groups projects and the people who work on them.
- **List API tools**: Returns every API tool in the environment. An API tool is a saved HTTP request an agent can make. The call takes no paging parameters, so one request yields the whole set.
- **List checks**: Returns every test check in its turn. A test check is one assertion about an agent turn, comparing the reply or the behaviour behind it. The call takes no paging parameters, so one request yields the whole set.
- **List documents**: Returns every document in the knowledge base. A document is a source the knowledge base retrieves from. The call takes no paging parameters, so one request yields the whole set.
- **List environments**: Returns every environment in the project. An environment is one draft-and-published copy of the agent. The call takes no paging parameters, so one request yields the whole set.
- **List evaluations**: Returns every evaluation in the project. An evaluation is a criterion a model scores past conversations against. The call takes no paging parameters, so one request yields the whole set.
- **List functions**: Returns every function in the environment. A function is custom JavaScript that runs in Voiceflow’s sandbox and returns through a named path. The call takes no paging parameters, so one request yields the whole set.
- **List integrations**: Returns the integrations a project can use and whether each is connected. `connectionType` says how credentials arrive: `api-key` ones connect through this API, `oauth` and `app` ones only through the Voiceflow UI.
- **List MCP servers**: Returns every MCP server in the environment. A MCP server is a registered Model Context Protocol server whose tools an agent can call. The call takes no paging parameters, so one request yields the whole set.
- **List MCP tools**: Returns every MCP tool in its server. A MCP tool is a tool an MCP server advertises, populated by syncing the server rather than by hand. The call takes no paging parameters, so one request yields the whole set.
- **List paths**: Returns every function path in its function. A function path is one of the named exits a function can return through. The call takes no paging parameters, so one request yields the whole set.
- **List playbooks**: Returns every playbook in the environment. A playbook is a set of instructions that drives an agent toward a goal, calling tools as it needs them. The call takes no paging parameters, so one request yields the whole set.
- **List projects**: Returns every project in the workspace. A project is the container that owns exactly one agent. The call takes no paging parameters, so one request yields the whole set.
- **List properties**: Returns every transcript property in the project. A transcript property is a label you define once and then set on individual conversations. The call takes no paging parameters, so one request yields the whole set.
- **List secret overrides**: Returns which environment versions hold a value of their own for each secret, as secret IDs grouped by environment alias and `draft` or `published` variant; values are never included. The call is unpaginated: it takes no paging parameters, so one request yields the whole set.
- **List secrets**: Returns the secrets defined on a project: name, visibility and whether a value has been stored for it, never the value itself. To learn which environment versions hold a value, use the override list. The call is unpaginated: it takes no paging parameters, so one request yields the whole set.
- **List tests**: Returns every test in the environment. A test is a scripted conversation replayed against the agent. The call takes no paging parameters, so one request yields the whole set.
- **List tools**: Returns every tool in the environment. A tool is something a playbook can call during a conversation. The call takes no paging parameters, so one request yields the whole set.
- **List transcript files**: Returns the files attached to one transcript that Voiceflow stores, each with a presigned download URL; files referenced only by an external URL are left out. The call is unpaginated: it takes no paging parameters, so one request yields the whole set.
- **List turns**: Returns every test turn in its test. A test turn is one side of a scripted conversation, either what the user says or the agent reply the checks assert on. The call takes no paging parameters, so one request yields the whole set.
- **List variables (API Tool Variable)**: Returns every API tool variable in its API tool. An API tool variable is an input an API tool substitutes into its request. The call takes no paging parameters, so one request yields the whole set.
- **List variables (Function Variable)**: Returns every function variable in its function. A function variable is an input or output a function declares. The call takes no paging parameters, so one request yields the whole set.
- **List variables (Variable)**: Returns every variable in the project. A variable is a named slot of project state an agent can read and write. The call takes no paging parameters, so one request yields the whole set.
- **List workspaces**: Returns every workspace in the account. A workspace is the container that groups projects and the people who work on them. The call takes no paging parameters, so one request yields the whole set.
- **Merge environments**: Folds the contents of one environment into another, so work done in a clone can be brought back to the environment it was cloned from.
- **Patch agent instructions**: Replaces one exact string in the main agent's routing instructions with another, matching literally on whitespace, punctuation and case. Quote `oldString` from a read or search result; with `replaceAll` off, more than one match is an error rather than a guess.
- **Patch playbook instructions**: Replaces one exact string in a playbook's instructions with another, matching literally on whitespace, punctuation and case. Quote `oldString` from a read or search result; with `replaceAll` off, more than one match is an error rather than a guess.
- **Patch the global prompt**: Replaces one exact string in the global prompt with another, matching literally on whitespace, punctuation and case. Quote `oldString` from a read or search result; with `replaceAll` off, more than one match is an error rather than a guess.
- **Publish environment**: Promotes the environment’s draft to its published version, which is the copy real traffic reaches. The request names the release so it can be told apart in the history.
- **Query API tool usage**: Reports how often each API tool was called, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query call count**: Reports how many voice calls were placed, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query call duration**: Reports how much time was spent on voice calls, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query category token usage**: Reports how many tokens each category consumed, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query daily token usage**: Reports how many tokens were consumed, bucketed by day, for one organization over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query entity token usage**: Reports how many tokens each entity consumed, for one organization over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query function usage**: Reports how often each function ran, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query hourly organization token usage**: Reports how many tokens were consumed, bucketed by hour, for one organization over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query hourly project token usage**: Reports how many tokens were consumed, bucketed by hour, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query integration usage**: Reports how often each integration ran, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query intent usage**: Reports how often each intent matched, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query knowledge base**: Searches the knowledge base and returns the passages a retrieval would surface, which is how to see what an agent will be grounded on before it answers.
- **Query knowledge base document usage**: Reports how often each knowledge base document was retrieved, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query MCP tool usage**: Reports how often each MCP tool was called, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query objective metrics**: Reports how sessions performed against the agent's configured objective, conversion or resolution, for one project over a date range. The request body takes `startDate` and `endDate`, with optional timezone, channel and environment filters.
- **Query organization token usage**: Reports how many tokens were consumed, for one organization over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query playbook usage**: Reports how often each playbook ran, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query project interaction count**: Reports how many interactions were exchanged, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query project token usage**: Reports how many tokens were consumed, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query project transcript count**: Reports how many conversations were recorded, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query prompt usage**: Reports how often each prompt was used, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query transcript cost**: Reports what those conversations cost in model spend, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query unique user count**: Reports how many distinct users held a conversation, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query workflow usage**: Reports how often each workflow ran, for one project over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query workspace interaction count**: Reports how many interactions were exchanged, for one workspace over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query workspace token usage**: Reports how many tokens were consumed, for one workspace over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Query workspace transcript count**: Reports how many conversations were recorded, for one workspace over a date range. The request body takes `startDate`, `endDate` and an `interval`, the same shape the other analytics measures take.
- **Read agent instructions**: Returns one page of the main agent's routing instructions, each line prefixed with its 1-based number, so a later patch can quote text exactly as it appears. `offset` and `limit` pick the page; the totals in the response cover the whole document.
- **Read playbook instructions**: Returns one page of a playbook's instructions, each line prefixed with its 1-based number, so a later patch can quote text exactly as it appears. `offset` and `limit` pick the page; the totals in the response cover the whole document.
- **Read the global prompt**: Returns one page of the global prompt, each line prefixed with its 1-based number, so a later patch can quote text exactly as it appears. `offset` and `limit` pick the page; the totals in the response cover the whole prompt.
- **Run evaluation**: Scores one finished conversation against an evaluation. The response carries the verdict together with the reasoning behind it, so a low score says why.
- **Search agent instructions**: Searches the main agent's routing instructions line by line with a JavaScript regular expression and returns one page of matching lines with surrounding context, up to `limit`; the match totals count the whole document.
- **Search playbook instructions**: Searches a playbook's instructions line by line with a JavaScript regular expression and returns one page of matching lines with surrounding context, up to `limit`; the match totals count the whole document.
- **Search runs**: Finds past runs of a test, each carrying how many of its checks passed. The body takes `take` and `skip`, so results arrive a page at a time rather than all at once.
- **Search the global prompt**: Searches the global prompt line by line with a JavaScript regular expression and returns one page of matching lines with surrounding context, up to `limit`; the match totals count the whole prompt.
- **Search transcripts**: Finds recorded conversations matching a filter. Unlike the list calls elsewhere in this API, the body takes `take` and `skip`, so results arrive a page at a time.
- **Send**: Advances a conversation by one turn: the body carries the action to apply, and the response carries the traces the agent produced in reply.
- **Set property value**: Sets a property’s value on one conversation. Defining the property and setting it are separate calls, so the definition is reused across every transcript that carries it.
- **Set secret value**: Sets a secret's value on one version of an environment. Without `environmentAlias` it writes the `main` environment's published version. With `environmentAlias`, pass `versionVariant` (`published` or `draft`) to name the version to write. The value is never read back; MCP clients cannot call this.
- **Sync MCP server**: Refreshes the stored list of tools an MCP server advertises, which is how MCP tools come to exist rather than being created by hand.
- **Update agent**: Changes the agent that shapes every turn - its global prompt, its routing instructions, or its settings - in the environment named by the request.
- **Update API tool**: Changes an existing API tool in place. The response carries only a confirmation message, so refetch the API tool to read its new values.
- **Update check**: Changes an existing test check in place. The response carries only a confirmation message, so refetch the test check to read its new values.
- **Update document**: Changes an existing document in place. The response carries only a confirmation message, so refetch the document to read its new values.
- **Update environment**: Changes an existing environment in place. The response carries only a confirmation message, so refetch the environment to read its new values.
- **Update evaluation**: Changes an existing evaluation in place. The response carries only a confirmation message, so refetch the evaluation to read its new values.
- **Update function**: Changes an existing function in place. The response carries only a confirmation message, so refetch the function to read its new values.
- **Update MCP server**: Changes an existing MCP server in place. The response carries only a confirmation message, so refetch the MCP server to read its new values.
- **Update path**: Changes an existing function path in place. The response carries only a confirmation message, so refetch the function path to read its new values.
- **Update playbook**: Changes an existing playbook in place. The response carries only a confirmation message, so refetch the playbook to read its new values.
- **Update project**: Changes an existing project in place. The response carries only a confirmation message, so refetch the project to read its new values.
- **Update property**: Changes an existing transcript property in place. The response carries only a confirmation message, so refetch the transcript property to read its new values.
- **Update state**: Changes the stored state of a live conversation, which is how a caller seeds or corrects variables between turns without replaying the conversation.
- **Update test**: Changes an existing test in place. The response carries only a confirmation message, so refetch the test to read its new values.
- **Update tool**: Changes an existing tool in place. The response carries only a confirmation message, so refetch the tool to read its new values.
- **Update traffic split**: Changes an existing environment in place. The response carries only a confirmation message, so refetch the environment to read its new values.
- **Update turn**: Changes an existing test turn in place. The response carries only a confirmation message, so refetch the test turn to read its new values.
- **Update variable (API Tool Variable)**: Changes an existing API tool variable in place. The response carries only a confirmation message, so refetch the API tool variable to read its new values.
- **Update variable (Function Variable)**: Changes an existing function variable in place. The response carries only a confirmation message, so refetch the function variable to read its new values.
- **Update variables**: Updates variables in the conversation state by merging with the properties in the request body.
- **Update variable (Variable)**: Changes an existing variable in place. The response carries only a confirmation message, so refetch the variable to read its new values.
- **Update workspace**: Changes an existing workspace in place. The response carries only a confirmation message, so refetch the workspace to read its new values.

Connect Voiceflow in General Input: https://www.generalinput.com/apps/voiceflow