How to Use Eleven Turbo v2 in Devin
Eleven Turbo v2 turns English scripts into speech for spoken replies and short voiceovers. ElevenLabs recommends Eleven Flash v2 instead, which offers equivalent functionality with lower average latency.
Prompts to try with Eleven Turbo v2 in Devin
Copy an example into Devin, or ask in your own words.
Use Eleven Turbo v2 to narrate a plain-English summary of this project's latest changelog entry. Keep the script under 700 characters and spell out version numbers as they should be spoken.
Read the README and use Eleven Turbo v2 to make an English introduction explaining the project's purpose. Keep the narration under 750 characters and expand acronyms before synthesis.
Use Eleven Turbo v2 to generate separate English narration clips for the walkthrough script in this project. Keep each section under 800 characters and preserve sentence boundaries.
Use Eleven Turbo v2 to compare two readings of the first paragraph in our demo script. Keep the voice and wording fixed, start stability at 0.5, and lower it slightly for the second take.
Use Eleven Turbo v2 to narrate the English training instructions in this project. Generate one clip per step, keep each under 800 characters, and insert a one-second SSML break before each step's final reminder.
How to set up Eleven Turbo v2 in Devin
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add a custom MCP
Open Customize › MCPs. Click + and choose New MCP. Fill in:
- Sign in to Spiral and approve
In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.
- Check it
On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.
Use the Spiral skill
- Send Devin 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 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 Turbo v2
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_turbo_v2", "input": { "text": "<text>", "voice_id": "<voice_id>" } }'
Then paste one of the prompts above: Devin finds Eleven Turbo v2 on Spiral, shows the price and runs it.
Eleven Turbo v2 providers and prices
Spiral runs Eleven Turbo v2 through ElevenLabs. Open a card for today's price, with every fee included.
Settings you can ask for
Eleven Turbo v2 works from your text, next text, and previous text. Ask Devin 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 Eleven Turbo v2 is on its tool page: open its card above.
What can you do with Eleven Turbo v2 in Devin?
Turn project documentation and release notes into English narration for demos, tutorials, and spoken updates. Your coding agent can prepare the script, expand technical abbreviations, and divide longer passages into short sections.
Spoken support replies
Turn an approved English answer into a short spoken response. Spell out reference numbers in the order the listener should hear them.
Product walkthrough narration
Create English narration for individual walkthrough scenes. Generate each scene separately so a script change requires replacing only that section.
Audio release notes
Convert a concise English release summary into a spoken update. Expand version numbers and technical abbreviations before synthesis.
Daily spoken briefings
Make an English audio briefing from approved updates. Keep each section short and write dates and quantities as spoken words.
Training instructions
Read English procedures aloud in separate steps. Add a short pause between instructions when listeners need time to act.
Narration draft comparisons
Generate short English readings of alternative scripts. Compare wording and stability settings before choosing a take.
Read-aloud article sections
Create an English audio edition of an article in sections under 800 characters. Review each section before assembling the full reading.
More on Eleven Turbo v2 and Devin
Overview
Eleven Turbo v2 in other agents
Questions about Eleven Turbo v2 in Devin
Can Devin use Eleven Turbo v2?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Eleven Turbo v2 like any built-in tool.
How much does Eleven Turbo v2 cost in Devin?
$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 Devin plan is separate.
Do I need an ElevenLabs account to use Eleven Turbo v2 in Devin?
No. Spiral runs Eleven Turbo v2 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 Turbo v2 in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Eleven Turbo v2 runs?
Eleven Turbo v2 runs in the background. Devin starts the run, checks on it and gives you the audio when it's ready.
Does Eleven Turbo v2 support languages other than English?
No. Eleven Turbo v2 supports English only, so use a multilingual speech model when your script includes another language.
How much audio can Eleven Turbo v2 generate at once?
ElevenLabs documents a limit of 30,000 characters per API request, roughly 30 minutes of speech. For better consistency, generate shorter sections; its troubleshooting guide recommends keeping sections under 800 characters.
How does Eleven Turbo v2 compare with Eleven Flash v2?
ElevenLabs describes the two as functionally equivalent, with lower average latency on Eleven Flash v2. It classifies Eleven Turbo v2 as deprecated and recommends Flash over Turbo.
Which settings should I adjust if the voice sounds flat?
Try lowering stability slightly to allow more emotional variation. Start around 50% stability, 75% similarity, and zero style exaggeration, then compare short samples.
How do I prevent mistakes with dates and acronyms?
Write them as you want them spoken before generating audio. For example, turn an ambiguous date into a spelled-out month and day, and separate letters in an acronym that should be read letter by letter.
Start using Eleven Turbo v2 in Devin
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Devin:
set up https://spiral.ai/SKILL.md


