Which text-to-speech models can the ElevenLabs node use?

The node supports several models, including Multilingual v2 for the highest quality across many languages, Turbo v2.5 for a fast high-quality balance, and Flash v2.5 for ultra-low latency. There is also a streaming text-to-speech operation suited to real-time playback.

Can I create a custom voice from my own recordings?

Yes. The Clone Voice from Audio Samples operation performs instant voice cloning from one to twenty-five base64-encoded audio samples. Once created, the voice can be selected in any text-to-speech or speech-to-speech operation, and its settings can be edited later.

Does ElevenLabs in NoClick support transcription and dubbing?

It does. Transcribe Audio to Text converts audio into text with the Scribe model across more than ninety languages. Create Dubbing Project re-voices a video or audio file into a target language, and you poll the dubbing status until it is ready.

How is audio passed in and out of the node?

Operations that consume audio, such as transcription, voice changing, and voice cloning, take base64-encoded audio data. Generated audio is returned by the operation, and you can also list generated audio history and download or fetch past history items.

How do I authenticate, and can I track usage?

The node uses an ElevenLabs API key generated under Account, Profile and API Key in your ElevenLabs settings. Because keys are tied to subscription limits, the node also exposes operations to get subscription information and character usage statistics.

What makes OpenCode different here?

OpenCode is open and model-agnostic, so you have flexibility over the underlying model. NoClick handles running it and connecting your apps as tools.

How do I give OpenCode tools?

Connect an integration node to the agent's tools handle and choose the operations to allow. Each becomes a tool the agent can call.

Do I manage any infrastructure?

No. NoClick runs the OpenCode harness in a hosted sandbox and resolves credentials for the apps you connect.

Can it combine several apps?

Yes. Add as many integrations as you need and the agent can use them together in one run.

Connect OpenCode to ElevenLabs

Plug ElevenLabs into an AI agent and it produces audio instead of only describing it. It can clone a voice from samples, isolate vocals from a track, start a dubbing project and check its status, create a pronunciation dictionary, edit voice settings, and download history items, each step a tool call it runs while it works. Wire it into a hosted coding agent in NoClick and it can take a batch of clips from raw audio to finished, dubbed output unattended.

Loading preview…

Opens a workflow with 31 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own OpenCode, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in ElevenLabs
A preset of real ElevenLabs operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect ElevenLabs
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your OpenCode first calls in. opencode mcp add only saves the config. OpenCode connects when it starts — run opencode, or restart a running one.
1. Run this in your terminal
$opencode mcp add
2. Choose Remote and paste your server URL
https://mcp.noclick.app/s/<your-link>
3. Choose No when asked about OAuth authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools OpenCode gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

ElevenLabs

31 tools

Convert Text to Speech

Convert text to speech

Stream Text to Speech Realtime

Stream text to speech in real-time

Convert Text to Speech with Timestamps

Convert text to speech with word-level timestamps

Convert Audio Using Voice

Convert audio using a voice (voice changer)

Transcribe Audio to Text

Transcribe audio to text

List Available Voices

List all available voices

Get Voice by Id

Get voice details by ID

Clone Voice from Audio Samples

Clone a voice from audio samples (Instant Voice Cloning)

Edit Voice Settings

Edit voice settings and metadata

Delete Custom Voice

Delete a custom voice

Generate Sound Effects from Text

Generate sound effects from text description

Isolate Vocals from Audio

Isolate vocals from audio

Create Dubbing Project

Create a dubbing project for video/audio

Get Dubbing Project Status

Get dubbing project status and metadata

Delete Dubbing Project

Delete a dubbing project

List Generated Audio History

List all generated audio history

Get History Item Details

Get a specific history item by ID

Delete History Item

Delete a history item

Get History Item Audio

Get audio file from history item

Download History Items

Download multiple history items

List Pronunciation Dictionaries

List all pronunciation dictionaries

Get Pronunciation Dictionary by Id

Get a pronunciation dictionary by ID

Create Pronunciation Dictionary

Create a pronunciation dictionary from rules

Delete Pronunciation Dictionary

Delete a pronunciation dictionary

Create Audio Native Project

Create an audio native project (embeddable audio player)

Get Audio Native Project Details

Get audio native project details

Delete Audio Native Project

Delete an audio native project

List Available Ai Models

List all available AI models

Get User Account Information

Get user account information

Get Subscription Information

Get subscription information and limits

Get Character Usage Stats

Get character usage statistics

Starting points

What you can build

Convert a block of text to speech with a chosen voice and model, tuning stability and similarity for the right delivery.

Generate text-to-speech with word-level timestamps so captions or subtitles can be aligned precisely to the audio.

Transcribe an uploaded audio file to text with the Scribe model, optionally specifying the language.

Clone a voice from audio samples and reuse it for announcements or narration across later workflow runs.

Create a dubbing project that re-voices a video into another language while preserving the original tone.

Generate a custom sound effect from a text description for use in video ads or product demos.

Meet the runner

About OpenCode

OpenCode is an open, model-agnostic command-line coding agent. In NoClick it runs hosted and gains your apps as tools, so it can act on real systems rather than just edit files. Wire an integration into the agent and OpenCode can use that app’s operations directly while it works. It is a flexible choice when you want an open agent with broad model support and real tool access.

Open and model-agnostic

Flexible across many underlying models

Good general-purpose tool use

Lightweight to point at a focused task

Good to know