How to Use HeyGen Voice in Gemini
Use HeyGen Voice for course narration, podcast scripts, and spoken app content. It follows the standard generation path; HeyGen Voice Turbo shortens that step when faster production matters.
Prompts to try with HeyGen Voice in Gemini
Copy an example into Gemini, or ask in your own words.
Write a 70-word introduction for a podcast episode about repairing everyday objects. Use HeyGen Voice to narrate it, with moderate expressiveness and no production directions in the spoken text.
Write a short welcome message for a neighborhood library app. Use HeyGen Voice to generate two reads of the same words, one with low expressiveness and one with higher expressiveness.
Write a brief explanation of how to organize a weekly meal plan. Use HeyGen Voice to narrate the same paragraph with two punctuation treatments so I can compare the pauses.
Read this paragraph aloud with HeyGen Voice in a calm, warm voice and give me the MP3.
Make a 30-second podcast intro voiceover with HeyGen Voice.
How to set up HeyGen Voice in Gemini
Pick the way that suits you. Each takes about two minutes.
Use the Gemini connector
- Open Connected Apps
On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.
- Add Spiral as a custom app
Under Custom apps, click Add a custom app and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Gemini 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 HeyGen Voice
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": "heygen/heygen-voice", "input": { "text": "Hello! This is HeyGen Voice, speaking on fal." } }'
Then paste one of the prompts above: Gemini finds HeyGen Voice on Spiral, shows the price and runs it.
HeyGen Voice providers and prices
Spiral runs HeyGen Voice through fal. Open a card for today's price, with every fee included.
Settings you can ask for
HeyGen Voice works from your text. Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Voice | Jonah, Nadine, Tabitha, Soren, Elowen, Vincent, Jocelyn, Marielle and 16 more | Jonah | HeyGen public voice. Ignored when reference_audio_url is set. |
| Language | ar, be, bg, ca, cs, da, de, el and 31 more | Language of the text. Detected from the text when omitted. | |
| Expressiveness boost | 0 to 1 | 1 | How expressive the delivery is. |
Every API field of HeyGen Voice is on its tool page: open its card above.
What can you do with HeyGen Voice in Gemini?
Turn a script discussed in chat into a podcast introduction, lesson, or product explanation. Compare short reads and refine the wording before producing longer narration.
Course lesson narration
Turn a lesson script into spoken instruction. Test one explanatory paragraph with lower expressiveness before producing the remaining sections.
App welcome messages
Create a spoken welcome that explains the app's first useful action. Keep the script focused on one task and review the opening sentence by ear.
Support reply audio
Convert an approved troubleshooting answer into a spoken response. Use short sentences and listen for pauses between instructions.
Podcast intros
Generate an introduction from the episode title and summary. Keep production directions outside the spoken script and audition the complete introduction.
Ad read comparisons
Produce several reads of approved ad copy with different expressiveness levels. Compare delivery while keeping the wording fixed.
Product walkthrough narration
Write a spoken explanation of a product workflow, then generate each section separately. Review terminology and pacing before adding the narration to the edit.
More on HeyGen Voice and Gemini
Overview
HeyGen Voice in other agents
Questions about HeyGen Voice in Gemini
Can Gemini use HeyGen Voice?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run HeyGen Voice like any built-in tool.
How much does HeyGen Voice cost in Gemini?
Each item in `text` adds $0.000039. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.
Do I need a fal account to use HeyGen Voice in Gemini?
No. Spiral runs HeyGen Voice on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up HeyGen Voice in Gemini?
About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.
Does Gemini wait while HeyGen Voice runs?
HeyGen Voice runs in the background. Gemini starts the run, checks on it and gives you the audio when it's ready.
How should I choose between HeyGen Voice and HeyGen Voice Turbo?
Turbo uses the same voices with a shorter generation step. Choose it when frequent revisions or repeated narration make speed useful; compare a representative passage before committing to a longer project.
What audio format does HeyGen Voice produce?
HeyGen Voice and HeyGen Voice Turbo produce 44.1 kHz WAV audio. That gives you an audio file to use in an editor or app.
How much expressiveness should I use?
Start lower for instructional narration and higher for an ad read. Zero gives the baseline delivery; compare the same sentence at different levels before generating the full script.
How should I write a script for HeyGen Voice?
Write complete sentences with enough context to establish the intended emotion. The model reads contextual cues, so test a complete paragraph rather than judging a voice from an isolated word.
Can I count on an exact emotional performance?
Text-to-speech can miss subtle tone, pacing, or emotion. Review important lines by ear and try revised wording or punctuation before approving the recording.
Start using HeyGen Voice in Gemini
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini:
set up https://spiral.ai/SKILL.md


