How to Use Eleven v4 in Hermes
Eleven v4 turns scripts into expressive narration for audiobooks, character voiceovers, and produced content. Compared with Eleven v4 Turbo, it prioritizes audio quality over conversational speed.
Prompts to try with Eleven v4 in Hermes
Copy an example into Hermes, or ask in your own words.
Each weekday, turn the approved update supplied to this task into a spoken briefing of no more than 150 words with Eleven v4. Use a measured delivery and pause between topics.
Every Monday, use the approved product change summary supplied to this task to generate a short walkthrough with Eleven v4. Keep it under 120 words and put a pause before each instruction.
Every Friday, generate a reading of the approved story excerpt supplied to this task with Eleven v4. Keep the script under 2,000 characters and place one clear emotional direction at each change in the scene.
Every Monday at 9am: read this paragraph aloud with Eleven v4 in a calm, warm voice and give me the MP3.
Make a 30-second podcast intro voiceover with Eleven v4.
How to set up Eleven v4 in Hermes
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Hermes 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 and sign in
Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.
hermes mcp add spiral \ --url https://api.spiral.ai/mcp \ --auth oauth \ --connect-timeout 300
- Check it
In a chat that was already open, run /reload-mcp.
hermes mcp list hermes mcp test spiral
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 v4
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": "fal", "model": "elevenlabs/tts/eleven-v4", "input": { "text": "[excited] Hello! Welcome to Eleven v4." } }'
Then paste one of the prompts above: Hermes finds Eleven v4 on Spiral, shows the price and runs it.
Eleven v4 providers and prices
Spiral runs Eleven v4 through fal. Open a card for today's price, with every fee included.
$0.104 per 1,000 characters of text. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Eleven v4 works from your text. Ask Hermes for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Stability | 0 to 1 | 0.5 | Voice stability. Lower values allow more expressive delivery; higher values make delivery more consistent. |
| Similarity boost | 0 to 1 | 0.75 | How closely the output follows the reference voice. Higher values increase similarity but may reduce naturalness. |
| Seed | 0 to 4294967295 | Seed for best-effort reproducibility. Identical output is not guaranteed. | |
| Output format | mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000 and 11 more | mp3_44100_128 | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. |
| Apply text normalization | auto, on, or off | auto | Whether to normalize text such as numbers and dates before generation. |
| Timestamps | on or off | off | Whether to return character-level timing information with the generated audio. |
Every API field of Eleven v4 · Text to Speech is on its tool page: open its card above.
What can you do with Eleven v4 in Hermes?
Produce recurring spoken updates with consistent script structure and deliberate delivery cues. A scheduled agent can prepare concise narration from the information supplied to each run and generate audio for review.
Product walkthrough narration
Turn a walkthrough script into spoken instructions. Use short delivery cues to distinguish an explanation from a warning or a successful result.
Game character lines
Generate quest instructions, reactions, and character monologues. Place emotional changes directly in the script so the performance follows the scene.
Localized voiceovers
Produce spoken versions of approved scripts in supported languages such as Spanish, French, Japanese, and Portuguese.
Spoken assistant responses
Give confirmations, explanations, and follow-up questions different deliveries. Use concise scripts with a clear direction at each change in tone.
Story narration
Read a short story or scene aloud with changes in emotion and pacing. Keep directions close to the passages they affect.
Performance previews
Try different deliveries of the same script before choosing a take. Compare a curious, restrained, or excited reading without changing the spoken words.
More on Eleven v4 and Hermes
Overview
Eleven v4 in other agents
Questions about Eleven v4 in Hermes
Can Hermes use Eleven v4?
Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run Eleven v4 like any built-in tool.
How much does Eleven v4 cost in Hermes?
Each item in `text` adds $0.104. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Hermes plan is separate.
Do I need a fal account to use Eleven v4 in Hermes?
No. Spiral runs Eleven v4 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Eleven v4 in Hermes?
About two minutes: add the server and sign in, then check it.
Does Hermes wait while Eleven v4 runs?
Eleven v4 runs in the background. Hermes starts the run, checks on it and gives you the audio when it's ready.
What is Eleven v4 useful for?
Use Eleven v4 speech generation when delivery matters: narration, character lines, localized voiceovers, and spoken assistant responses. Write the words to be spoken, then add short bracketed directions where the performance should change.
Which languages does Eleven v4 support?
Eleven v4 and Eleven v4 Turbo support more than 90 languages, including English, Spanish, French, Japanese, and Portuguese. Provide the script in the language you want spoken.
How do I control emotion and delivery?
Place short directions such as [whispers], [curious], or [sighs] immediately before the words they affect. Introduce a new direction at the point where delivery should change, and avoid conflicting directions on the same phrase.
Why might an audio tag produce an unexpected sound?
The model can interpret an ambiguous tag as a sound effect instead of a vocal direction. Describe the intended delivery explicitly, such as [low, gravelly voice], and test the line before using it.
Start using Eleven v4 in Hermes
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Hermes:
set up https://spiral.ai/SKILL.md


