Skip to content
Latest Effects
Start creating
Output reference for Flash v2.5 Audio / Text to speech
  • ElevenLabs
  • Standard
  • Generate audio

Flash v2.5

Generate multilingual speech fast enough for responsive voice experiences.

Half the wait, a little less nuance.

  • Text to speech

Curated output references.

Current API configuration

What goes in. What comes back.

The model defines every slot it reads and every result it returns. Required inputs must be present before a run can begin.

Inputs

Prompts and source material

Prompt

Text · Required

Previous text

Text · Optional

Next text

Text · Optional

Outputs

Files and structured results

Audio

Audio

Available controls

Configure the run.

Control Available values Requirement
Output format mp3_44100_128 Optional
Voice String Required
Language en, ja, zh, de, hi, fr, ko, pt, it, es, id, nl, tr, fil, pl, sv, bg, ro, ar, cs, el, fi, hr, ms, sk, da, ta, uk, ru, hu, no, vi Optional
Stability 0–1 · step 0.01 Optional
Similarity boost 0–1 · step 0.01 Optional
Style 0–1 · step 0.01 Optional
Speed 0.7–1.2 · step 0.01 Optional
Speaker boost On, Off Optional
Seed Integer Optional

Works especially well for

  • Text to speech
  • Productions that need audio
  • Keeping generated results beside the edit and references

Know the trade-offs

  • Generation results are probabilistic and need editorial review.
  • Availability, speed and final price can change with the provider.
  • The public catalogue does not include vendor benchmarks or model-specific artwork.

Configure the model.
Keep the result in the cut.

The generation returns to the scene, asset folder and timeline it belongs to.

Start creating