[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Eleven v3 Conversational](https://spiral.ai/integrations/instinct/eleven-v3-conversational)

# How to Use Eleven v3 Conversational in Instinct

Eleven v3 Conversational turns written responses into expressive speech for support conversations, tutoring, and interactive characters. Compared with Eleven v3, it is optimized for real-time dialogue, with audio tags to guide delivery.

|  |  |
| --- | --- |
| Model | Eleven v3 Conversational |
| Available through | ElevenLabs |
| Category | Audio |
| Price | $0.052 per 1,000 characters of `text`. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Eleven v3 Conversational in Instinct

- Every weekday morning, turn my approved priorities into a spoken briefing with Eleven v3 Conversational. Keep it under 150 words, spell out dates, and use a calm conversational tone.
- Each Monday, create one beginner French conversation question with an English explanation and generate the French question with Eleven v3 Conversational. Keep the question under 20 words.
- Each afternoon, turn the approved service update into a spoken message with Eleven v3 Conversational. Keep it under 100 words and use reassuring language when the update describes a delay.
- Every Friday, summarize the approved weekly accomplishments in three sentences and generate audio with Eleven v3 Conversational. Expand abbreviations and keep the delivery warm.
- Each morning, generate one short fictional mystery clue with Eleven v3 Conversational. Keep it under 40 words and place a whisper cue before the final sentence.

## How to set up Eleven v3 Conversational in Instinct

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send Instinct this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **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

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Eleven v3 Conversational**: One request; the result comes back by polling or a webhook.

```bash
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_conversational",
    "input": {
      "text": "<text>",
      "voice_id": "<voice_id>"
    }
  }'
```

Then paste one of the prompts above: Instinct finds Eleven v3 Conversational on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

## Eleven v3 Conversational tools and prices

- [Eleven v3 Conversational](https://spiral.ai/tools/elevenlabs/eleven_v3_conversational) (ElevenLabs): $0.052 per 1,000 characters of `text`.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | 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. |
| next_text |  | — | The text that comes after the text of the current request. |
| audio_effects |  | — | Audio effects applied to the generated audio. |
| language_code |  | — | Language code (ISO 639-1) used to enforce a language for the model and text normalization. |
| 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, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000 | mp3_44100_128 | Output format of the generated audio. |
| previous_text |  | — | The text that came before the text of the current request. |

## What can you do with Eleven v3 Conversational in Instinct?

Make recurring summaries and reminders available as spoken updates with Eleven v3 Conversational. Have the scheduled agent prepare concise scripts from approved information and spell out dates and abbreviations before generation.

### Customer support responses

Use Eleven v3 Conversational to voice short support replies. Write a calm acknowledgment followed by one concrete next step, then audition the delivery.

### Language practice

Generate short Spanish, French, or German conversation turns with Eleven v3 Conversational. Keep the written transcript alongside each recording for practice.

### Interactive character replies

Give a game character short spoken reactions with Eleven v3 Conversational. Try curiosity, sarcasm, or a whispered line to explore the character's delivery.

### Spoken troubleshooting

Turn a troubleshooting answer into a short spoken explanation with Eleven v3 Conversational. Expand technical abbreviations and read each instruction as a complete sentence.

### Localized service messages

Create separate German, Spanish, French, Portuguese, and Hindi service messages with Eleven v3 Conversational. Review each recording with its intended audience before reuse.

### Conversational daily briefings

Use Eleven v3 Conversational to turn an approved daily summary into a short spoken update. Spell out dates and abbreviations so the script reads clearly aloud.

### Support training exercises

Produce individual customer or representative lines with Eleven v3 Conversational for training exercises. Compare a reassuring response with a direct response to the same complaint.

## Overview

- [ElevenLabs](https://spiral.ai/providers/elevenlabs)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## Eleven v3 Conversational in other agents

- [Amp](https://spiral.ai/integrations/amp/eleven-v3-conversational)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/eleven-v3-conversational)
- [Claude](https://spiral.ai/integrations/claude-desktop/eleven-v3-conversational)
- [Claude Code](https://spiral.ai/integrations/claude-code/eleven-v3-conversational)
- [Cline](https://spiral.ai/integrations/cline/eleven-v3-conversational)
- [Codex](https://spiral.ai/integrations/codex/eleven-v3-conversational)
- [Cursor](https://spiral.ai/integrations/cursor/eleven-v3-conversational)
- [Devin](https://spiral.ai/integrations/devin/eleven-v3-conversational)
- [dots](https://spiral.ai/integrations/dots/eleven-v3-conversational)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/eleven-v3-conversational)
- [Gemini](https://spiral.ai/integrations/gemini/eleven-v3-conversational)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/eleven-v3-conversational)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/eleven-v3-conversational)
- [goose](https://spiral.ai/integrations/goose/eleven-v3-conversational)
- [Grok](https://spiral.ai/integrations/grok/eleven-v3-conversational)
- [Grok Build](https://spiral.ai/integrations/grok-build/eleven-v3-conversational)
- [Hermes](https://spiral.ai/integrations/hermes/eleven-v3-conversational)
- [Manus](https://spiral.ai/integrations/manus/eleven-v3-conversational)
- [Muse](https://spiral.ai/integrations/muse/eleven-v3-conversational)
- [Muse Code](https://spiral.ai/integrations/muse-code/eleven-v3-conversational)
- [n8n](https://spiral.ai/integrations/n8n/eleven-v3-conversational)
- [Notion](https://spiral.ai/integrations/notion/eleven-v3-conversational)
- [OpenClaw](https://spiral.ai/integrations/openclaw/eleven-v3-conversational)
- [opencode](https://spiral.ai/integrations/opencode/eleven-v3-conversational)
- [Perplexity](https://spiral.ai/integrations/perplexity/eleven-v3-conversational)
- [Raycast](https://spiral.ai/integrations/raycast/eleven-v3-conversational)
- [VS Code](https://spiral.ai/integrations/vscode/eleven-v3-conversational)
- [Windsurf](https://spiral.ai/integrations/windsurf/eleven-v3-conversational)
- [Zapier](https://spiral.ai/integrations/zapier/eleven-v3-conversational)

## More Instinct guides

- [Eleven v3](https://spiral.ai/integrations/instinct/eleven-v3)
- [Eleven v4](https://spiral.ai/integrations/instinct/eleven-v4)
- [Eleven Turbo v2](https://spiral.ai/integrations/instinct/eleven-turbo-v2)
- [Eleven v4 Turbo](https://spiral.ai/integrations/instinct/eleven-v4-turbo)
- [Eleven Sound Effects v3](https://spiral.ai/integrations/instinct/eleven-sound-effects-v3)
- [ElevenLabs Audio Isolation](https://spiral.ai/integrations/instinct/elevenlabs-audio-isolation)

## Questions about Eleven v3 Conversational in Instinct

**Can Instinct use Eleven v3 Conversational?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Eleven v3 Conversational like any built-in tool.

**How much does Eleven v3 Conversational cost in Instinct?**

$0.052 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 Instinct plan is separate.

**Do I need an ElevenLabs account to use Eleven v3 Conversational in Instinct?**

You need no ElevenLabs account. Instinct uses one Spiral API key for every tool, and Spiral runs Eleven v3 Conversational on its own ElevenLabs account.

**How long does it take to set up Eleven v3 Conversational in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Eleven v3 Conversational runs?**

Eleven v3 Conversational runs in the background. Instinct starts the run, checks on it and gives you the audio when it's ready.

**What is Eleven v3 Conversational best suited for?**

Use it for spoken responses where tone matters: reassuring a customer, giving encouraging feedback, or performing a character's reply. It builds on Eleven v3 with optimization for real-time dialogue.

**How do I control emotion and delivery?**

Add square-bracket audio tags such as [laughs] or [whispers] where the delivery should change. Start with a short passage and listen before applying the same direction throughout a script.

**Which languages does Eleven v3 Conversational support?**

It supports more than 70 languages. ElevenLabs specifically highlights German, Spanish, French, Portuguese, and Hindi as strengths.

**How much text can I generate at once?**

Vercel documents a limit of 5,000 characters per request for Eleven v3 Conversational. Keep individual passages below that limit and split longer scripts at complete sentences.

**What weaknesses should I listen for?**

Check accent consistency when targeting UK or Australian English. Salesforce's integration documentation reports that these accents can be less reliable with Eleven v3 Conversational.

