How to Use Eleven v3 in OpenClaw
Use Eleven v3 for expressive voiceovers, narration, and character performances in 70+ languages. Inline audio tags direct whispers, laughter, and emotional shifts, though the chosen voice affects how well those directions work.
Prompts to try with Eleven v3 in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every weekday, use Eleven v3 to narrate a summary of that morning's public space-science news. Link the sources, keep the script under 3,000 characters, and use a steady tone with pauses between stories.
Each Monday, write an original English vocabulary lesson and narrate it with Eleven v3. Keep the script under 2,000 characters and add [pause] between each word and its example sentence.
Every Friday, use Eleven v3 to generate English and French audio editions of a short public astronomy update. Verify the information first and keep each script under 3,000 characters.
Each evening, create an original mystery installment under 2,500 characters and narrate it with Eleven v3. Keep the narrator's voice consistent and use [whispers] only when the scene calls for it.
Every Sunday, use Eleven v3 to record a short history lesson based on public museum sources. Include the source links, keep the script under 3,000 characters, and pause between the event and its explanation.
How to set up Eleven v3 in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Eleven v3
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "elevenlabs", "model": "eleven_v3", "input": { "text": "<text>", "voice_id": "<voice_id>" } }'
Then paste one of the prompts above: OpenClaw finds Eleven v3 on Spiral, shows the price and runs it.
Eleven v3 providers and prices
Spiral runs Eleven v3 through ElevenLabs. Open a card for today's price, with every fee included.
Settings you can ask for
Eleven v3 works from your text, next text, and previous text. Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. | |
| Output format | alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96 and 20 more | mp3_44100_128 | Output format of the generated audio. |
| Use pvc as ivc | on or off | Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency. | |
| Apply text normalization | auto, on, or off | auto | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. |
| Optimize streaming latency | a whole number | You can turn on latency optimizations at some cost of quality. | |
| Apply language text normalization | on or off | off | This parameter controls language text normalization. |
Every API field of ElevenLabs v3 Text to Speech is on its tool page: open its card above.
What can you do with Eleven v3 in OpenClaw?
Produce recurring audio editions of summaries, lessons, and updates. A scheduled agent can prepare a fresh script for each run and generate it with Eleven v3 using a consistent voice and delivery plan.
Product demonstration narration
Turn a demonstration script into a voiceover. Add pauses between actions and generate separate sections for review against the video.
Game character performances
Create alternate readings of character dialogue with whispered warnings, laughter, or emotional shifts. Choose a voice suited to the character's delivery.
Audiobook scene drafts
Generate short narrative passages to test pacing and emotional direction. Split chapters into sections below the 5,000-character limit.
Multilingual educational narration
Create separate English, French, and German recordings from reviewed lesson scripts. Use pauses to separate an explanation from its example.
Advertisement reading comparisons
Generate restrained and excited readings of the same advertisement script. Compare delivery before choosing the recording for editing.
Podcast introductions
Record introductions and episode transitions from prepared scripts. Test where a pause or a change in tone helps the listener follow the story.
Spoken article summaries
Turn an edited article summary into a listening version. Keep each script within the character limit and use a steady delivery for factual passages.
Eleven v3 success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| ElevenLabs v3 Text to Speech | 100.0% | 4.3s | 474 |
More on Eleven v3 and OpenClaw
Overview
Eleven v3 in other agents
Questions about Eleven v3 in OpenClaw
Can OpenClaw use Eleven v3?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run Eleven v3 like any built-in tool.
How much does Eleven v3 cost in OpenClaw?
$0.104 per 1,000 characters of text. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.
Do I need an ElevenLabs account to use Eleven v3 in OpenClaw?
No. Spiral runs Eleven v3 on its own ElevenLabs account. You sign in to Spiral once and never paste a key.
How long does it take to set up Eleven v3 in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while Eleven v3 runs?
Eleven v3 runs in the background. OpenClaw starts the run, checks on it and gives you the audio when it's ready.
What is Eleven v3 good at?
Eleven v3 suits narration and character performances that need emotional changes, whispers, laughter, or sighs. Use inline audio tags to direct those changes within the script.
How much speech can Eleven v3 generate at once?
The input limit is 5,000 characters. ElevenLabs estimates roughly five minutes of audio at that length, so split longer scripts into sections and measure the resulting recordings.
Which languages does Eleven v3 support?
Eleven v3 supports 70+ languages, including English, French, and German. Check the supported-language list before planning a translation project.
How do I control emotion and pacing?
Place a short direction in square brackets where the delivery should change, such as [whispers] or [laughs]. Pacing cues include [pause], [rushed], and [drawn out].
Can I specify pauses with SSML?
Eleven v3 does not support SSML break tags. Use audio tags, punctuation, and paragraph structure to shape pauses instead.
Start using Eleven v3 in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


