How to Use Gemini 3.8 Flash-Lite TTS in Devin
Gemini 3.8 Flash-Lite TTS turns written scripts into speech for bulk narration, read-aloud features, and voice agents. Choose it for everyday speech; Gemini 3.8 Flash TTS is better suited to detailed acting, difficult pronunciation, and regional dialects.
Prompts to try with Gemini 3.8 Flash-Lite TTS in Devin
Copy an example into Devin, or ask in your own words.
Read the project's getting-started documentation and draft a 150-word spoken introduction. Use Gemini 3.8 Flash-Lite TTS to generate calm narration, keeping delivery instructions separate from the transcript.
Find the onboarding tutorial scripts in this project. Use Gemini 3.8 Flash-Lite TTS to generate one narration clip per section, with a short pause between instructions and each request below 8,192 input tokens.
Turn the latest changelog entry into an 80-word spoken release summary. Use Gemini 3.8 Flash-Lite TTS with matter-of-fact delivery and save the recording beside the release assets.
Use the customer service examples in the project to write a six-turn training conversation. Generate it with Gemini 3.8 Flash-Lite TTS using two prebuilt voices, keeping speaker labels outside the spoken transcript.
Take the approved product demo script in this project and generate three recordings with Gemini 3.8 Flash-Lite TTS: calm, upbeat, and neutral. Keep the spoken words identical so I can compare delivery.
How to set up Gemini 3.8 Flash-Lite TTS 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 Gemini 3.8 Flash-Lite TTS
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": "gemini", "model": "gemini-3.8-flash-lite-tts", "input": { "contents": [ {} ] } }'
Then paste one of the prompts above: Devin finds Gemini 3.8 Flash-Lite TTS on Spiral, shows the price and runs it.
Gemini 3.8 Flash-Lite TTS providers and prices
Spiral runs Gemini 3.8 Flash-Lite TTS through Gemini and Vertex AI. Open a card for today's price, with every fee included. Name one in your prompt, or let Devin pick.
Up to $0.255617 per run at the default inputs. $1.30 per 1M text input tokens, $15.60 per 1M audio output tokens.
Up to $0.255617 per run at the default inputs. $1.30 per 1M text input tokens, $15.60 per 1M audio output tokens.
What can you do with Gemini 3.8 Flash-Lite TTS in Devin?
Create spoken tutorials, help content, and training clips from text already in your project. Have your coding agent prepare the scripts and use Gemini 3.8 Flash-Lite TTS to generate section-by-section narration.
Help article narration
Turn approved support articles into spoken explanations, with pauses between instructions.
Product tutorial voiceovers
Generate narration from a reviewed tutorial script. Produce a separate clip for each section so editors can revise individual passages.
Localized narration
Produce spoken editions of approved translations for training, product education, or informational videos.
Audio newsletters
Convert an edited newsletter into a spoken edition with a brief introduction and pauses between stories.
Voice agent responses
Speak the responses another agent has already written, using brief delivery directions for reassurance or explanation.
Customer service training
Record short customer-and-representative conversations with two prebuilt voices and separate delivery directions for each turn.
Read-aloud lessons
Create spoken versions of reviewed lessons, adding pauses after questions so learners have time to think.
Voiceover delivery comparisons
Generate the same approved script with calm, upbeat, and matter-of-fact delivery for an editor to compare.
More on Gemini 3.8 Flash-Lite TTS and Devin
Overview
Gemini 3.8 Flash-Lite TTS in other agents
Questions about Gemini 3.8 Flash-Lite TTS in Devin
Can Devin use Gemini 3.8 Flash-Lite TTS?
Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Gemini 3.8 Flash-Lite TTS like any built-in tool.
How much does Gemini 3.8 Flash-Lite TTS cost in Devin?
Up to $0.255617 per run at the default inputs. $1.30 per 1M text input tokens, $15.60 per 1M audio output tokens. 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 Gemini account to use Gemini 3.8 Flash-Lite TTS in Devin?
No. Spiral runs Gemini 3.8 Flash-Lite TTS on its own Gemini account. You sign in to Spiral once and never paste a key.
How long does it take to set up Gemini 3.8 Flash-Lite TTS in Devin?
About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.
Which provider runs Gemini 3.8 Flash-Lite TTS?
Spiral offers Gemini 3.8 Flash-Lite TTS through Gemini and Vertex AI. Name one in your prompt, or let Devin pick.
Does Devin wait while Gemini 3.8 Flash-Lite TTS runs?
Gemini 3.8 Flash-Lite TTS runs in the background. Devin starts the run, checks on it and gives you the audio when it's ready.
When should I choose Gemini 3.8 Flash-Lite TTS over Gemini 3.8 Flash TTS?
Choose Gemini 3.8 Flash-Lite TTS for bulk narration, read-aloud features, and everyday voice agent speech. Google favors Gemini 3.8 Flash TTS for detailed acting, difficult pronunciation, regional dialects, and complex dialogue.
How many languages does Gemini 3.8 Flash-Lite TTS support?
It supports more than 100 languages. Prepare and review the script in the intended language before generating its spoken version.
How much text and audio can Gemini 3.8 Flash-Lite TTS handle per request?
Google documents an 8,192-token input limit and a 16,384-token output serving limit. For long narration, divide the script into sections that fit those limits.
What audio format does Gemini 3.8 Flash-Lite TTS produce?
Complete responses default to a WAV file containing 24 kHz mono, 16-bit PCM audio. Use that specification when preparing audio for editing or playback.
Can Gemini 3.8 Flash-Lite TTS generate a conversation?
Yes. A single request supports two speakers using prebuilt voices, making it useful for short interviews, training conversations, and question-and-answer recordings.
Start using Gemini 3.8 Flash-Lite TTS 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


