How to Use Inworld TTS-1.5 Max in Devin
Inworld TTS-1.5 Max turns written scripts into expressive speech for narration, dialogue, and spoken responses. Compared with Inworld TTS-1.5 Mini, it prioritizes voice quality over the lowest latency.
Prompts to try with Inworld TTS-1.5 Max in Devin
Copy an example into Devin, or ask in your own words.
Use Inworld TTS-1.5 Max to narrate the main feature explained in this project's README. Write a plain-English script under 1,500 characters, generate the audio, and save the script beside it.
Use Inworld TTS-1.5 Max to create audio for the onboarding copy in this project. Generate one clip per screen, keep each script under 2,000 characters, and exclude button labels that interrupt the explanation.
Use Inworld TTS-1.5 Max to voice five representative lines from this project's dialogue files. Keep each line separate and include a pronunciation test for the main character's name.
Use Inworld TTS-1.5 Max to create a spoken version of this project's shortest help article. Split at paragraph boundaries if needed, keep each request under 2,000 characters, and save numbered clips.
Use Inworld TTS-1.5 Max to narrate the English and Spanish onboarding scripts in this repository. Preserve the reviewed wording, choose a native-language voice for each script, and generate separate clips under 2,000 characters each.
How to set up Inworld TTS-1.5 Max 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 Inworld TTS-1.5 Max
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": "fal-ai/inworld-tts", "input": { "text": "Hello! This is a demo of Inworld'\''s TTS." } }'
Then paste one of the prompts above: Devin finds Inworld TTS-1.5 Max on Spiral, shows the price and runs it.
Inworld TTS-1.5 Max providers and prices
Spiral runs Inworld TTS-1.5 Max through fal. Open a card for today's price, with every fee included.
$0.013 per 1,000 characters of text. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Inworld TTS-1.5 Max works from your text. Ask Devin for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Voice | Loretta (en), Darlene (en), Marlene (en), Hank (en), Evelyn (en), Celeste (en), Pippa (en), Tessa (en) and 105 more | Craig (en) | The voice to use for synthesis. |
| Sample rate hertz | 8000, 16000, 24000, 32000, 40000, or 48000 | 48000 | The sample rate in Hz for the output audio. |
Every API field of Inworld TTS-1.5 Max is on its tool page: open its card above.
What can you do with Inworld TTS-1.5 Max in Devin?
Give product walkthroughs, help content, and character dialogue a spoken version directly from project text. Have the coding agent prepare short scripts, check their lengths, and generate a clip for each section.
Product walkthrough narration
Turn a short feature explanation into spoken narration. Generate one clip per section so a changed feature only requires a new section.
Spoken support answers
Read approved answers about returns, delivery, or account features aloud. Start with concise scripts and audition names and abbreviations.
Character dialogue
Create separate spoken lines for an interactive story or game. Test the actual dialogue before committing to a voice.
Article summaries to hear
Convert a written summary into an audio briefing. Keep each request under 2,000 characters and retain the text for reference.
Lesson narration
Give short explanations an audio version. Insert a timed pause between a question and its answer for self-paced practice.
Localized voiceovers
Generate speech from reviewed translations. Pair each translation with a voice whose native language matches the script.
Read-aloud help content
Make short help articles and instructions available as speech. Split longer articles into clearly labeled sections.
Recurring audio briefings
Turn a daily written digest into a short spoken update. Keep the script focused on confirmed changes and omit sections with no news.
More on Inworld TTS-1.5 Max and Devin
Overview
Inworld TTS-1.5 Max in other agents
Questions about Inworld TTS-1.5 Max in Devin
Can Devin use Inworld TTS-1.5 Max?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Inworld TTS-1.5 Max like any built-in tool.
How much does Inworld TTS-1.5 Max cost in Devin?
Each item in `text` adds $0.013. 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 a fal account to use Inworld TTS-1.5 Max in Devin?
No. Spiral runs Inworld TTS-1.5 Max on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Inworld TTS-1.5 Max in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Does Devin wait while Inworld TTS-1.5 Max runs?
Inworld TTS-1.5 Max runs in the background. Devin starts the run, checks on it and gives you the audio when it's ready.
What is Inworld TTS-1.5 Max good for?
It suits expressive narration, character dialogue, and spoken assistant responses. Compared with Inworld TTS-1.5 Mini, it puts more emphasis on voice quality.
How much text can I turn into speech at once?
Keep each request within 2,000 characters. For longer scripts, split at sentence or paragraph boundaries and generate separate clips.
Can Inworld TTS-1.5 Max speak multiple languages?
Yes. Its launch coverage described support for 15 languages; for the closest match to a voice's identity, use text in that voice's native language.
Can I direct emotion with bracketed instructions?
Do not rely on instructions such as bracketed requests to whisper or sound excited. Inworld documents natural language steering as a TTS-2 capability, so audition the voice and script for the delivery you need.
How can I correct a mispronounced name?
Replace the troublesome word with its English IPA pronunciation inside slashes. Apply corrections one word at a time and listen to a short test before generating the full passage.
Start using Inworld TTS-1.5 Max 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


