What can you do with this server?

This server provides an MCP interface for the RunAPI InfiniteTalk model, allowing AI agents to create audio-to-video tasks, monitor their status, and check pricing. * audio_to_video: Submit a task to generate a video from an audio source using the infinitetalk-from-audio model. Supports an optional source image URL, output resolution (480p or 720p), and can either wait for completion or return immediately with a task ID. * get_task: Poll the current status and result payload (including output URLs) for a previously created task using its ID. * check_pricing: Retrieve the current pricing snapshot for the InfiniteTalk model and endpoints — no API key required.

How do I use infinitetalk-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@infinitetalk-mcp Turn this audio file into a video using the InfiniteTalk model" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

infinitetalk-mcp

by runapi-ai

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Why This Package?

@runapi.ai/infinitetalk-mcp is a focused Model Context Protocol server for the InfiniteTalk model line on RunAPI. It gives MCP-compatible assistants direct access to 1 endpoint and 1 model variant without loading the full RunAPI catalog.

Use this per-model server when an agent should stay scoped to InfiniteTalk. Use @runapi.ai/mcp when one assistant should discover every RunAPI model line.

Related MCP server: @runapi.ai/gpt-4o-image-mcp

Install

Add it to Claude Code:

claude mcp add infinitetalk -s user -- npx -y @runapi.ai/infinitetalk-mcp

Use project scope when the server should be shared with a repository:

claude mcp add infinitetalk -s project -- npx -y @runapi.ai/infinitetalk-mcp

Codex, Cursor, Windsurf, VS Code, Roo Code, and other MCP hosts can use the same stdio command:

{
  "mcpServers": {
    "infinitetalk": {
      "command": "npx",
      "args": ["-y", "@runapi.ai/infinitetalk-mcp"]
    }
  }
}

check_pricing works before sign-in. For task creation and status polling, ask your assistant to call the login tool. It opens a browser login and saves credentials to ~/.config/runapi/config.json, the same file used by runapi login. Headless and CI hosts can still set RUNAPI_API_KEY before starting the MCP host.

Ready-made examples are in examples/ for Claude, Cursor, Windsurf, VS Code, and Roo Code.

Tools

Tool	Auth	Purpose
`audio_to_video`	Yes	Create an InfiniteTalk audio to video task and optionally wait for a terminal status. Returns the task id, status, and output URLs.
`get_task`	Yes	Fetch the current status and latest payload for an existing task.
`check_pricing`	No	Look up current pricing for a InfiniteTalk model and endpoint.

Models

InfiniteTalk covers 1 model variant across 1 endpoint. Each tool accepts the models listed for it:

Tool	Models
`audio_to_video`	`infinitetalk-from-audio`

Model availability can change between releases. Use check_pricing or the InfiniteTalk model page for the current catalog view.

Agent Prompts

Ask your assistant in natural language; it can inspect pricing, create the task, and return the task id plus output URLs.

Create a task

Run an InfiniteTalk audio to video task with RunAPI.

The assistant can call check_pricing, then audio_to_video, and return the task id, status, and output URLs.

Submit without waiting

Create the task but don't wait for it to finish.

The assistant calls the create tool with wait: false and returns the task id. Check on it later with get_task.

Check pricing before creating

Check current InfiniteTalk pricing, then create the task if it matches my request.

The assistant calls check_pricing and can link to the InfiniteTalk model page for the canonical catalog entry.

Configuration

The server resolves auth in this order:

RUNAPI_API_KEY environment variable, useful for headless and CI hosts
~/.config/runapi/config.json, created by the MCP login tool or runapi login
No key, which still allows check_pricing

The config file is normally managed by login. A pre-provisioned headless config can use:

{
  "apiKey": "your_runapi_key"
}

Do not commit real API keys.

Links

Resource	URL
InfiniteTalk model page	https://runapi.ai/models/infinitetalk
npm package	@runapi.ai/infinitetalk-mcp
GitHub repository	runapi-ai/infinitetalk-mcp
RunAPI MCP overview	runapi.ai/mcp
RunAPI docs	runapi.ai/docs

License

Licensed under the Apache License, Version 2.0.

Available Tools

4 tools

audio_to_videoB

Create a InfiniteTalk task on RunAPI (audio to video). Returns a task id, status, and output URLs.

ParametersJSON Schema

Name	Required	Description
`seed`	No	Declared type: integer.
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`prompt`	No	Declared type: string.
`timeout_ms`	No
`callback_url`	No	Declared type: string.
`poll_interval_ms`	No
`source_audio_url`	Yes	Declared type: string.
`source_image_url`	Yes	Declared type: string.
`output_resolution`	No	Declared type: string. Known values: "480p", "720p".

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose the async task model and the return shape (task id, status, output URLs). It omits cost/credit implications (a check_pricing sibling exists), auth requirements (a login sibling exists), typical generation latency, and what happens when polling times out.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and target, and the second sentence delivers the only return-value information available since no output schema exists. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter asynchronous generation tool with no annotations and no output schema, the description leaves major gaps: authentication requirements, cost, the meaning of 'wait' versus callback_url, and the timeout/poll-interval behavior. The return-shape sentence is the only genuinely useful addition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 80%, but most entries are placeholder text like 'Declared type: string', so the schema conveys little semantic meaning. The description adds nothing about seed, prompt, model, callback_url, timeout_ms, or poll_interval_ms, so it neither compensates nor detracts; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Create') and resource ('InfiniteTalk task on RunAPI (audio to video)'), so an agent can tell it apart from the retrieval sibling get_task. It does not explicitly name competing tools, but the create-vs-fetch distinction is inferable from the verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus get_task or check_pricing, no mention of whether credentials/login are prerequisites, and no note that the built-in 'wait' polling may make a separate get_task call unnecessary. Usage is only implied by the tool name and inputs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

check_pricingC

Look up RunAPI pricing for the infinitetalk model line.

ParametersJSON Schema

Name	Required	Description	Default
`model`	No	Model slug. Defaults to the line's primary model.
`action`	No	Endpoint name. Defaults to the endpoint that offers the model.

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. "Look up" implies a safe read, but there is no disclosure of auth requirements, rate limits, caching/staleness of pricing data, or whether the `action` default silently picks an endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with the verb and resource front-loaded and no filler. It is efficient, though borderline under-specified for a tool with zero annotation coverage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (2 optional params, fully described schema, no nested objects, no output schema), so the description need not explain return values. It is minimally viable but leaves out any behavioral context that annotations would normally supply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both `model` and `action` are already documented in the schema with their defaults and enum, establishing a baseline of 3. The description adds no parameter-level meaning beyond the schema and arguably narrows scope to one model line.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("look up RunAPI pricing") and scopes it to a model line, so an agent knows exactly what this returns. It is distinguishable from the unrelated siblings (audio_to_video, get_task, login), though it does not explicitly say so. The hardcoded "infinitetalk model line" slightly undersells the parameterized `model` argument in the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this versus alternatives, no prerequisite, and no indication of when pricing lookup is or isn't appropriate. The only implicit guidance is that the sibling set contains no competing pricing tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_taskB

Fetch the current status and latest result payload for a infinitetalk task.

ParametersJSON Schema

Name	Required	Description	Default
`action`	No	Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint.
`task_id`	Yes	Task id returned when the task was created.

TDQS

B3.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose that the operation is a read ('Fetch') and that it returns the 'latest' result payload, which distinguishes it from a full-history fetch, but it says nothing about auth requirements, error/terminal states, result expiry, or whether repeated calls are safe.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero filler; the verb and returned data are stated immediately. Nothing redundant or restating the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description is the only source of return-value framing. It names status and result payload, which is a reasonable minimum, but leaves polling behavior, terminal states, and error handling unspecified for an async-task status tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so task_id and the action enum are already fully documented in the schema. The description adds no additional meaning about either parameter, which is the expected baseline 3 when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Fetch') and resource ('status and latest result payload for a infinitetalk task'), so an agent knows exactly what the call returns. It does not explicitly differentiate itself from siblings like audio_to_video, but the resource is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, no note that this is the polling counterpart to audio_to_video, and no advice on polling cadence or when to stop polling. The usage is only implied by the word 'status' and the async-task framing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

loginA

Authenticate RunAPI by opening a browser PKCE login flow and saving the API key to ~/.config/runapi/config.json.

ParametersJSON Schema

Name	Required	Description	Default
`force`	No	Re-run browser login when the current credential comes from the local config file.

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses the interactive browser flow and the file write side effect (config.json). However, it does not mention that it may overwrite existing credentials or that it could block waiting for user input, though these are implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the action ('Authenticate RunAPI') and provides necessary details without extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple login tool with one optional parameter and no output schema, the description covers the core purpose and side effect. It lacks an explicit statement that this is a prerequisite for other tools, but that is implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the only parameter 'force' has a description). The tool description adds no additional meaning about parameters beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Authenticate'), target resource ('RunAPI'), method ('browser PKCE login flow'), and side effect (saving to config.json). It is distinct from sibling tools, none of which relate to authentication.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (to authenticate RunAPI) but does not explicitly say when to run it (e.g., before other RunAPI tools) or when to use the 'force' parameter. Since there are no alternative auth tools among siblings, 'vs alternatives' is not applicable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesv0.2.0Oct 5, 2026
- Changedaudio_to_video12 fields changed
  - changedInput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```
  - addedInput schema / properties / callback_url / description
```
Added value: +"Declared type: string."
```
  - removedInput schema / properties / model / enum
```
Removed value: -[
-  "infinitetalk-from-audio"
-]
```
  - addedInput schema / properties / output_resolution / description
```
Added value: +"Declared type: string. Known values: \"480p\", \"720p\"."
```
  - removedInput schema / properties / output_resolution / enum
```
Removed value: -[
-  "480p",
-  "720p"
-]
```
  - addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
  - addedInput schema / properties / prompt / description
```
Added value: +"Declared type: string."
```
  - addedInput schema / properties / seed / description
```
Added value: +"Declared type: integer."
```
  - changedInput schema / properties / seed / type
```
Previous value: -"number"New value: +"integer"
```
  - addedInput schema / properties / source_audio_url / description
```
Added value: +"Declared type: string."
```
  - addedInput schema / properties / source_image_url / description
```
Added value: +"Declared type: string."
```
  - addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```
- Changedcheck_pricing2 fields changed
  - removedInput schema / additionalProperties
```
Removed value: -false
```
  - removedInput schema / properties / model / enum
```
Removed value: -[
-  "infinitetalk-from-audio"
-]
```
- Changedget_task1 field changed
  - removedInput schema / additionalProperties
```
Removed value: -false
```

2 tool updatesv0.1.7Aug 5, 2026

Changedaudio_to_video6 fields changed
- addedInput schema / properties / callback_url
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / prompt
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / seed
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / source_audio_url / type
```
Added value: +"string"
```
- addedInput schema / properties / source_image_url / type
```
Added value: +"string"
```
- addedInput schema / required
```
Added value: +[
+  "source_image_url",
+  "source_audio_url"
+]
```

Changedget_task1 field changed

changedInput schema / properties / action / description

Previous value: -"Endpoint the task was created on. Defaults to the line's only endpoint."New value: +"Asynchronous endpoint the task was created on. Defaults to the line's only asynchronous endpoint."

1 tool updatev0.1.6Jul 13, 2026
- Addedlogin
3 tool updatesv0.1.0Jun 24, 2026
- First observedaudio_to_video
- First observedcheck_pricing
- First observedget_task

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored 2026-10-05 07:50 across 4 tools

Disambiguation5/5

Each tool targets a clearly distinct action: task creation (audio_to_video), task polling (get_task), pricing lookup (check_pricing), and authentication (login). There is no overlap or risk of misselection between any pair.

Naming Consistency4/5

Three tools follow a clean verb_noun snake_case pattern (audio_to_video, get_task, check_pricing), and login is a single verb that still reads naturally. Minor deviation but overall predictable.

Tool Count4/5

Four tools is slightly thin but well-matched to a single-model wrapper: submit a job, poll it, check cost, authenticate. Nothing extraneous, though the surface is minimal.

Completeness3/5

The create-and-poll lifecycle plus auth and pricing is covered, but there is no way to list tasks, cancel/delete a task, or retrieve results separately from status. For a task-based async API, missing cancellation and enumeration are notable gaps.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Related MCP Connectors

mcp-klingOAuth
io.github.AceDataCloud
MCP server for Kling AI video generation
Image & Video Processing AI & Machine Learning
21
PixapiOAuth
io.github.Pixapi-AI
MCP server for Pixapi: check live credit pricing and balance, then generate images and video.
Image & Video Processing AI & Machine Learning
1
ViewMax MCP A
net.viewmaxstudio
Generate AI video from any MCP client. Pick the model, see the per-second price before you spend.
AI & Machine Learning Image & Video Processing
41
mcp-wanOAuth
io.github.AceDataCloud
MCP server for Wan AI video generation
AI & Machine Learning Image & Video Processing
21

Related MCP Servers

@runapi.ai/gemini-omni-mcp
AI & Machine Learning Multimedia Processing
runapi-ai
A
license
A
quality
A
maintenance
MCP server for the Gemini Omni model line, enabling task creation (audio, character, text-to-video) and pricing checks through RunAPI.
Updated 8 days ago (2026-09-30 11:30 UTC)
6
289 npm
Apache 2.0
@runapi.ai/gpt-4o-image-mcpofficial
AI & Machine Learning Image & Video Processing
runapi-ai
A
license
B
quality
A
maintenance
MCP server for GPT-4o Image model line, enabling text-to-image task creation, status polling, and pricing checks via RunAPI.
Updated 8 days ago (2026-09-30 11:30 UTC)
4
273 npm
Apache 2.0
imagen-4-mcp
AI & Machine Learning Image & Video Processing
runapi-ai
A
license
A
quality
A
maintenance
RunAPI MCP server for the Imagen 4 model line. Create tasks, poll their status, and check pricing through a single RunAPI API key.
Updated 8 days ago (2026-09-30 11:34 UTC)
5
254 npm
Apache 2.0
@runapi.ai/runway-aleph-mcpofficial
AI & Machine Learning Multimedia Processing
runapi-ai
A
license
A
quality
A
maintenance
MCP server for the Runway Aleph model line. Enables creating edit video tasks, polling status, and checking pricing through a single RunAPI API key.
Updated 8 days ago (2026-09-30 11:38 UTC)
4
274 npm
Apache 2.0

Why This Package?

Install

Tools

Models

Agent Prompts

Create a task

Submit without waiting

Check pricing before creating

Configuration

Links

License

Available Tools

TDQS

TDQS

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

@runapi.ai/gemini-omni-mcp

@runapi.ai/gpt-4o-image-mcpofficial

imagen-4-mcp

@runapi.ai/runway-aleph-mcpofficial