How to Use ElevenLabs Turbo v2.5 in opencode
ElevenLabs Turbo v2.5 turns scripts into speech in 32 languages for conversational replies and narration. ElevenLabs describes Flash v2.5 as functionally equivalent, with lower average latency.
Prompts to try with ElevenLabs Turbo v2.5 in opencode
Copy an example into opencode, or ask in your own words.
Use ElevenLabs Turbo v2.5 to narrate the getting-started section of this project's README. Rewrite it for spoken delivery, omit code blocks and URLs, and generate separate clips with scripts under 800 characters.
Use ElevenLabs Turbo v2.5 to create narration for the onboarding screens in this repository. Write one short clip per screen, preserve the UI labels, and keep all production instructions outside the spoken text.
Use ElevenLabs Turbo v2.5 to generate previews of the English dialogue in this project's game script. Create one clip per line, start with stability at 0.5 and style at zero, and keep character names out of the spoken audio.
Use ElevenLabs Turbo v2.5 to narrate the Spanish tutorial text in this repository. Use a voice suited to Mexican Spanish, expand dates and abbreviations into spoken words, and split the script into sections under 800 characters.
Use ElevenLabs Turbo v2.5 to turn this project's release notes into an audio walkthrough. Explain the three most useful changes in plain language, spell out version numbers as they should sound, and generate a separate clip for each change.
How to set up ElevenLabs Turbo v2.5 in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode 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 ElevenLabs Turbo v2.5
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_5", "input": { "text": "<text>", "voice_id": "<voice_id>" } }'
Then paste one of the prompts above: opencode finds ElevenLabs Turbo v2.5 on Spiral, shows the price and runs it.
ElevenLabs Turbo v2.5 providers and prices
Spiral runs ElevenLabs Turbo v2.5 through ElevenLabs. Open a card for today's price, with every fee included.
Settings you can ask for
ElevenLabs Turbo v2.5 works from your text, next text, and previous text. Ask opencode 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 Turbo v2.5 Text to Speech is on its tool page: open its card above.
What can you do with ElevenLabs Turbo v2.5 in opencode?
Add spoken walkthroughs, game dialogue previews, and training narration to a project with ElevenLabs Turbo v2.5. Use project text to prepare short scripts, then review pronunciation and delivery before adding the audio to the build.
Spoken support replies
Turn a written support answer into a short spoken response. Expand dates, reference numbers, and abbreviations before generating the audio.
Product walkthrough narration
Create a separate narration clip for each screen or action in a product demonstration, so a changed step needs only one replacement clip.
Localized training clips
Prepare training scripts in supported languages, then generate each language separately with a voice suited to its accent.
Daily audio briefings
Convert a written daily summary into a spoken briefing. Write dates and figures as they should be read and divide the briefing by topic.
Game dialogue previews
Generate individual spoken lines from a game script to review wording and delivery before assembling a scene.
Language practice recordings
Create recordings of short practice sentences in supported languages. Use a voice with the intended accent and review pronunciation before sharing.
Article audio editions
Turn an edited article into spoken sections. Generate and review short passages individually when consistency or pronunciation needs attention.
More on ElevenLabs Turbo v2.5 and opencode
Overview
ElevenLabs Turbo v2.5 in other agents
Questions about ElevenLabs Turbo v2.5 in opencode
Can opencode use ElevenLabs Turbo v2.5?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run ElevenLabs Turbo v2.5 like any built-in tool.
How much does ElevenLabs Turbo v2.5 cost in opencode?
$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 opencode plan is separate.
Do I need an ElevenLabs account to use ElevenLabs Turbo v2.5 in opencode?
No. Spiral runs ElevenLabs Turbo v2.5 on its own ElevenLabs account. You sign in to Spiral once and never paste a key.
How long does it take to set up ElevenLabs Turbo v2.5 in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while ElevenLabs Turbo v2.5 runs?
ElevenLabs Turbo v2.5 runs in the background. opencode starts the run, checks on it and gives you the audio when it's ready.
What is ElevenLabs Turbo v2.5 best suited for?
Use it to turn written replies and scripts into spoken audio, especially for conversational applications. It also fits short narration tasks such as product walkthroughs and training clips.
How much speech can ElevenLabs Turbo v2.5 generate at once?
The limit is 40,000 characters per request, which ElevenLabs estimates as about 40 minutes of audio. For longer scripts, shorter sections make it easier to review pronunciation and replace a weak passage.
Which languages does ElevenLabs Turbo v2.5 support?
It supports 32 languages, including English, Spanish, French, German, Japanese, Chinese, Hindi, Hungarian, Norwegian, and Vietnamese. Choose a voice suited to the target language and regional accent.
Which voice settings should I adjust first?
Start around 50% stability and 75% similarity, with style exaggeration at zero. Lower stability for more emotional variation or raise it for steadier delivery, listening for a tone that becomes too flat.
How do I avoid awkward pronunciation and spoken stage directions?
Spell out numbers, dates, symbols, and acronyms the way they should sound. Keep delivery instructions outside the speech text because descriptive directions can be read aloud.
Start using ElevenLabs Turbo v2.5 in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


