Firefly Speech
Firefly Speech converts supplied text into spoken audio. The Generate Speech interface lets the user select a voice and adjust language, accent, speed and pitch. Adobe’s own model is a separate choice from the partner ElevenLabs Multilingual v2 model.
Pronunciation can be edited before the final export
The editor includes pronunciation guidance, tone controls and pauses. Preview selected text to inspect names and specialist terms. These controls make the workflow more specific than choosing a voice and generating a complete script without review.Generate speech with Firefly Speech
Language and accent are separate choices
Adobe lists US and Indian English, Canadian and French French, and several Spanish locales separately. Choose the intended audience’s locale rather than assuming the language name describes every delivery option.Firefly Speech languages and accents
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Provider product |
| Input | Typed text or imported TXT and DOCX files.Generate speech with Firefly Speech |
| Published language coverage | Dutch, English, French, German, Hindi, Italian, Mandarin and Spanish, with specified regional accents.Firefly Speech languages and accents |
| Listed credit rate | 10 Adobe generative credits per 1,000 characters; plan conditions apply.Adobe generative-credit rates and plan conditions |
Related models
- Firefly Sound Effects Model
Adobe · Firefly Audio
Sound-effects model that uses text to describe sounds and optional voice input to control timing and energy.
Launch date Provider product - Firefly Music Model
Adobe · Firefly Audio
Adobe’s model for instrumental background music, with mood, style, tempo and duration controls for video and other media.
Launch date not confirmedProvider product