How to Use Gemini 3.8 Flash TTS in Gemini CLI
Gemini 3.8 Flash TTS turns scripts into expressive narration and two-speaker dialogue. Choose it for audiobooks, regional accents, and scenes that need detailed acting direction.
Prompts to try with Gemini 3.8 Flash TTS in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Read the project's onboarding documentation and draft a 150-word spoken walkthrough. Use Gemini 3.8 Flash TTS to narrate it with clear, measured delivery, keeping performance directions outside the spoken text.
Find the latest release notes and prepare a 120-word audio summary without adding claims. Generate narration with Gemini 3.8 Flash TTS, using a matter-of-fact tone.
Take a two-character scene from the project's dialogue scripts. Generate it with Gemini 3.8 Flash TTS using two distinct speakers, separate directions for each turn, and a <short pause> before the final reply.
Use the project's approved tutorial copy to produce a short voiceover with Gemini 3.8 Flash TTS. Keep the transcript verbatim and put slow, clear delivery instructions in separate turn-level metadata.
Create two readings of the first paragraph of the project's introduction with Gemini 3.8 Flash TTS. Try one without style directions and one with a brief warm delivery direction so I can compare them.
How to set up Gemini 3.8 Flash TTS in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI 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 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-tts", "input": { "contents": [ {} ] } }'
Then paste one of the prompts above: Gemini CLI finds Gemini 3.8 Flash TTS on Spiral, shows the price and runs it.
Gemini 3.8 Flash TTS providers and prices
Spiral runs Gemini 3.8 Flash TTS through Gemini and Vertex AI. Open a card for today's price, with every fee included. Name one in your prompt, or let Gemini CLI pick.
Up to $0.383412 per run at the default inputs. $1.30 per 1M text input tokens, $23.40 per 1M audio output tokens.
Up to $0.383412 per run at the default inputs. $1.30 per 1M text input tokens, $23.40 per 1M audio output tokens.
What can you do with Gemini 3.8 Flash TTS in Gemini CLI?
Turn project documentation and dialogue scripts into narration you can review alongside the product. Your coding agent can prepare the transcript and separate performance directions before sending text to Gemini 3.8 Flash TTS.
Audiobook narration
Turn an edited chapter into spoken narration, with delivery directions kept separate from the prose. Produce longer books in sections.
Scripted podcast dialogue
Record a host-and-guest script with two distinct speakers and separate acting directions for each turn.
Game dialogue
Produce character lines with directed emotion, breaths, sighs, and pauses for dialogue review.
Regional narration
Create narration for a target language and regional accent. Review a short pronunciation sample before recording the complete script.
Product walkthrough voiceovers
Turn an approved walkthrough script into spoken instructions, with pauses between actions and clear delivery.
Audio editions of articles
Create a narrated edition of edited article text for readers who prefer listening.
Training conversations
Record two-person practice scenes, such as a customer asking a question and an employee explaining the answer.
Recurring spoken briefings
Convert an agent's checked daily summary into narration with a consistent delivery brief.
More on Gemini 3.8 Flash TTS and Gemini CLI
Gemini 3.8 Flash TTS in other agents
Questions about Gemini 3.8 Flash TTS in Gemini CLI
Can Gemini CLI use Gemini 3.8 Flash TTS?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Gemini 3.8 Flash TTS like any built-in tool.
How much does Gemini 3.8 Flash TTS cost in Gemini CLI?
Up to $0.383412 per run at the default inputs. $1.30 per 1M text input tokens, $23.40 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 Gemini CLI plan is separate.
Do I need a Gemini account to use Gemini 3.8 Flash TTS in Gemini CLI?
No. Spiral runs Gemini 3.8 Flash 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 TTS in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Which provider runs Gemini 3.8 Flash TTS?
Spiral offers Gemini 3.8 Flash TTS through Gemini and Vertex AI. Name one in your prompt, or let Gemini CLI pick.
Does Gemini CLI wait while Gemini 3.8 Flash TTS runs?
Gemini 3.8 Flash TTS runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.
What is Gemini 3.8 Flash TTS good at?
It suits audiobooks, studio narration, and dialogue where acting and pronunciation matter. Regional accents and brief vocal reactions also make it useful for character scenes.
Can Gemini 3.8 Flash TTS generate two voices?
Yes. A multi-speaker request requires exactly two speakers, making it suitable for interviews, host-and-guest scripts, and dialogue scenes.
Which languages does Gemini 3.8 Flash TTS support?
Google documents 132 languages, including support for regional accents and minority dialects. Listen to a short sample in your target dialect before producing a longer recording.
How long can a Gemini 3.8 Flash TTS request be?
The Gemini API documents an input limit of 8,192 tokens and an output serving limit of 16,384 tokens. Plan longer narration as separate sections and check each recording's ending.
What audio format does Gemini 3.8 Flash TTS produce?
Complete, nonstreaming responses default to WAV with 24 kHz mono, 16-bit PCM audio.
Start using Gemini 3.8 Flash TTS in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


