Seedance 2.5 is here. Every model is included on every plan.
PricingLog inSign up
VoiceGoogle

Gemini 2.5 Pro TTS

Gemini 2.5 Pro TTS is Google's studio quality speech model, with a curated voice set and multi speaker scene support. Reach for it when you want clean, neutral narration at a low price per word.

Voices30 available
Make with Gemini 2.5 Pro TTS →View pricing

Added July 2026. Included on every plan.

Why this one

What makes Gemini 2.5 Pro TTS different

  1. Studio clean outputVery low noise and artefact rate, which means less cleanup before it reaches an edit.
  2. Multi speaker scenesMore than one voice in a single generation, for interviews and two handers.
  3. A curated voice setThirty voices rather than hundreds, which makes casting a choice rather than a search.
  4. Low cost per thousand charactersAmong the cheapest speech on Dolly, which suits long scripts.
  5. Neutral, professional deliveryIt reads straight, which is what corporate and explainer work usually wants.
  6. Consistent across long scriptsPace and tone hold from the first paragraph to the last.

Use cases

Best for

  • Corporate narration
  • Explainer voiceover
  • E learning
  • Interview style scenes
  • Documentation audio
  • Long form reads

Technique

Prompt tips

  1. Write plainlyNeutral delivery suits plain prose. Flowery script writing fights the voice rather than helping it.
  2. Use paragraph breaksThey become real pauses and they are the main pacing control.
  3. Label speakers for scenesMulti speaker output needs clear turns in the text.
  4. Audition two or three voicesThirty is a short enough list to actually listen through the plausible ones.
  5. Render long scripts in sectionsEasier to fix one paragraph than to re run everything.

Mechanism

How Gemini 2.5 Pro TTS works

You pick a voice, or several for a scene, and supply the script; the model renders speech directly from the text and bills by the characters sent. Its character is restraint: it does less interpretation than the expressive models, which is why it is the better pick for informational content and the worse pick for drama.

Getting started

How to use it on Dolly

  1. Pick Gemini 2.5 Pro TTSChoose it in the voice studio, or just ask the agent for it by name.
  2. Write the promptDescribe what you want, in as much detail as the brief deserves.
  3. GenerateThe exact credit cost sits on the button before you press it, and a failed run refunds automatically.

Pricing

What it costs

Every generation shows its exact credit cost on the button before you run it.

per 1,000 characters
6 credits

One run is about 1/208 of a Starter month.

Failed generations refund automatically. See plans

Capabilities

Specs

Voices
30

Questions

Gemini 2.5 Pro TTS FAQ

How many voices are there?
Thirty, all listed on this page, which is short enough to audition the plausible ones rather than search.
Can it do multiple speakers?
Yes, multi speaker scenes are supported in a single generation.
How is it priced?
Per thousand characters, and it is one of the cheaper voice models here.
Is it expressive?
Deliberately less so than the ElevenLabs models. Pick it for clarity, not for drama.
What languages does it handle?
The voice list on this page is the authoritative set for what is available on Dolly.

More like this

Other voice models

ElevenLabs Multilingual V2ElevenLabs Multilingual V2 is the classic ElevenLabs voice model, with the largest voice library on Dolly and consistently lifelike delivery.ElevenLabs V3ElevenLabs V3 is the expressive ElevenLabs model, capable of multi voice dialogue in a single generation.KokoroKokoro is a fast, open source speech model with twenty American voices and the lowest price per word on Dolly.

Ready to make with Gemini 2.5 Pro TTS?

Every model is included on every plan. The price sits on the button before you run it.

Start making →