01Narration
Choose the voice for the message.
Pick from thirty voices for a product explanation, educational clip or voice-over. Listen to names, numbers and technical terms before publishing.
✨ Create Stunning Videos with AI! Access Kling 3.0, Seedance, Veo, Flux, Nano Banana and more in one platform. Start Creating
Google · AI audio
Gemini 3.8 Flash TTS, give the script its own voice.
Use one voice for narration or two for a scripted exchange. Keeping delivery instructions separate from spoken text helps you change tone without rewriting the actual message.
30 voicesTwo-speaker dialogueSeparate delivery direction
HighReach audio suiteGemini 3.8 Flash TTS
Prompt direction
A: What changes when we shorten the opening? B: The benefit arrives sooner. Keep the demonstration and remove the repeated introduction.
BriefGenerateReview
Illustrative artwork generated with Nano Banana Pro via fal. Not a sample output or benchmark of this model. Supporting imagery is illustrative too.
Voices
30 selectable voices
Modes
Single narrator or two speakers
Direction
Separate style instructions
HighReach input limit
8,000 UTF-8 bytes including directions
Why Gemini 3.8 Flash TTS?
One narrator or two speakers. A script you control.
A practical creative workflow for explainer voice-overs and more.
01
Use one voice for narration or two for a scripted exchange. Keeping delivery instructions separate from spoken text helps you change tone without rewriting the actual message.
02
Useful starting points include explainer voice-overs, two-person product demonstrations, short conversational educational clips. Choose one specific outcome for the first pass.
03
The controls below describe what is available in HighReach, not every option in the underlying API. This is scripted speech, not a live conversational agent or voice clone.
Gemini 3.8 Flash TTS capabilities
Direct the performance, not just the words.
Explore what Gemini 3.8 Flash TTS supports in HighReach, with controls and limits that match the current integration.
01
02Scripted dialogue
Write both sides of the conversation.
Enable dialogue, select two voices and prefix each line with A: or B:. This is a scripted recording workflow, not a live agent or a voice clone.
03Delivery direction
Change the tone, not the words.
Keep pacing, energy and performance notes separate from the spoken script. Both script and style text contribute to the character-based estimate.
Connected production
Brief, generate, compare, and refine without losing the creative thread.
How it works
Your first audio creation, in three decisions.
Prepare the brief, choose the controls that matter, then review a small first pass before a larger production run.
01
Prepare the creative brief
Choose a narrator, or enable dialogue and select two voices.
02
Choose your direction
In dialogue mode, begin each line with A: or B:.
03
Generate, review and refine
Add delivery direction separately, generate the audio and listen through before editing it into the timeline.
Model lineup in HighReach
Choose your Gemini 3.8 Flash TTS workflow.
Open the right tool with the model already selected. Check the live settings and credit estimate before submitting.
Create narration or dialogue
Narration and dialogue
Switch between a single narrator and two configured speakers in Create Voice Over.
- Thirty voice choices
- A: / B: dialogue lines
- Separate style instructions
Plan your generation
Know the cost before you create.
Normal pricing. No temporary launch discount built into your quote.
Normal provider pricing is $0.045 per 1,000 characters. HighReach counts script and style text for its estimate and applies its existing audio margin. Dialogue is priced from its turns, not from an assumed recording length.
Credits include HighReach's service margin. The tool recalculates the estimate for your settings and references. Actual token usage and output length can differ from an estimate.
Compare HighReach plans →Example credit estimate
121
credits
1,000 script characters, no extra style text
This configuration only—not an unlimited plan or a guaranteed price for every result.
Check your settings →Prompt playbook
Write better Gemini 3.8 Flash TTS prompts.
A useful prompt behaves like a compact director's brief. Give every detail a job instead of stacking visual adjectives.
Separate the content from performance or musical direction.
Listen to the entire output before using it in a finished edit.
Use material you own or have permission to use.
Starting brief
01Explainer voice-overs
A: What changes when we shorten the opening? B: The benefit arrives sooner. Keep the demonstration and remove the repeated introduction.
Another direction
02Give an explainer a calmer delivery
Script: Start with one clear idea. Show the result, explain the first step, and leave the viewer with something they can try. Style direction: Warm, conversational and unhurried. Pause briefly between sentences. Avoid an exaggerated advertising voice.
Choose the right model
Compare Gemini 3.8 Flash TTS with other audio models.
No single model is best for every brief. Compare the controls, cost and results that matter for your production workflow.
MiniMaxMiniMax Music 3
Explore original campaign music concepts
Generate music from a style brief and lyrics with MiniMax Music 3 in HighReach. Set a duration cap up to five minutes and export WAV audio.
Explore MiniMax Music 3Production notes
What to check before the final export.
Check 01
This is scripted speech, not a live conversational agent or voice clone.
Check 02
The API has an 8,192-token input limit; HighReach uses a more conservative byte cap.
Check 03
Check pronunciations, pacing and speaker transitions before placing the track in a finished video.
Gemini 3.8 Flash TTS FAQ
Questions before you generate.
Practical answers about Gemini 3.8 Flash TTS, available HighReach workflows, output controls, and prompt direction.
01Can I add a third speaker?
Not in this integration. Dialogue uses exactly two configured speakers, while narration uses a single voice.
02How do I use Gemini 3.8 Flash TTS in HighReach?
Choose a narrator, or enable dialogue and select two voices. In dialogue mode, begin each line with A: or B:. Add delivery direction separately, generate the audio and listen through before editing it into the timeline.
03How much does Gemini 3.8 Flash TTS cost?
Normal provider pricing is $0.045 per 1,000 characters. HighReach counts script and style text for its estimate and applies its existing audio margin. Dialogue is priced from its turns, not from an assumed recording length. Your HighReach credit estimate includes the service margin and is recalculated in the tool.
Model notes & sources
Capabilities and normal rates checked against provider documentation on September 27, 2026. These are workflow recommendations, not benchmark results. Page artwork is illustrative and was generated with Nano Banana Pro via fal; it is not a sample output of Gemini 3.8 Flash TTS.
Gemini 3.8 Flash TTS in HighReach
Make your next idea with Gemini 3.8 Flash TTS.
Bring a focused brief to HighReach. Choose your settings, check the quote, and start with one carefully directed result.