@runapi.ai/elevenlabs-mcp

text_to_speech

Generate spoken audio from written text using ElevenLabs AI. Returns a task ID, status, and output URLs for the created speech.

Instructions

Create a ElevenLabs task on RunAPI (text to speech). Returns a task id, status, and output URLs.

Input Schema

TableJSON Schema

Name	Required	Description
`text`	Yes	Declared type: string.
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`speed`	No	Declared type: number.
`style`	No	Declared type: number.
`voice`	No	Declared type: string.
`next_text`	No	Declared type: string.
`stability`	No	Declared type: number.
`timeout_ms`	No
`timestamps`	No	Declared type: boolean.
`callback_url`	No	Declared type: string.
`language_code`	No	Declared type: string.
`previous_text`	No	Declared type: string.
`poll_interval_ms`	No
`similarity_boost`	No	Declared type: number.

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.2.0Oct 5, 2026
- changedInput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```
- addedInput schema / properties / callback_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / language_code / description
```
Added value: +"Declared type: string."
```
- removedInput schema / properties / model / enum
```
Removed value: -[
-  "text-to-speech-multilingual-v2",
-  "text-to-speech-turbo-v2.5"
-]
```
- addedInput schema / properties / next_text / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / previous_text / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / similarity_boost / description
```
Added value: +"Declared type: number."
```
- addedInput schema / properties / speed / description
```
Added value: +"Declared type: number."
```
- addedInput schema / properties / stability / description
```
Added value: +"Declared type: number."
```
- addedInput schema / properties / style / description
```
Added value: +"Declared type: number."
```
- addedInput schema / properties / text / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / timestamps / description
```
Added value: +"Declared type: boolean."
```
- addedInput schema / properties / voice / description
```
Added value: +"Declared type: string."
```
Changed12 schema fields changedv0.1.7Aug 5, 2026
- addedInput schema / properties / callback_url
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / language_code
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / next_text
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / previous_text
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / similarity_boost
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / speed
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / stability
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / style
```
Added value: +{
+  "type": "number"
+}
```
- addedInput schema / properties / text / type
```
Added value: +"string"
```
- addedInput schema / properties / timestamps
```
Added value: +{
+  "type": "boolean"
+}
```
- addedInput schema / properties / voice
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / required
```
Added value: +[
+  "text"
+]
```
First observedv0.1.0Jun 23, 2026

TDQS

B3.2/5.0

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 usefully discloses that the call is asynchronous and returns a task id, status, and output URLs, which implies a task-based workflow. However, it omits auth/permission needs, cost implications, whether the returned task may still be pending, and how wait/poll_interval_ms/timeout_ms interact.

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?

Two short sentences with the action and return shape front-loaded, and no filler. It is slightly terse given the 15-parameter surface, but nothing is wasted.

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?

For a 15-parameter, no-output-schema tool, the description covers the return contract (task id, status, output URLs) but says nothing about the model/voice/audio-tuning parameters or the polling behavior. With 87% schema coverage the structured fields do most of the work, but the description leaves real gaps.

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 87%, so the schema already documents most parameters (e.g., wait as 'Poll until the task reaches a terminal status'). The description adds no parameter-level meaning beyond that, so the baseline of 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?

The description states a specific verb (Create), resource (ElevenLabs task on RunAPI), and clarifies the modality as text-to-speech, which distinguishes it from siblings like speech_to_text, text_to_sound, and text_to_dialogue. It does not explicitly name which sibling to use instead, but the purpose 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 guidance on when to use this tool versus text_to_sound, text_to_dialogue, or speech_to_text, nor any mention of when to set wait=true versus polling get_task manually. The agent is left to infer usage entirely from the name.

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

Deploy Server

text_to_speech

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools