bannerbannerExperience Now
WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Speech Generation/elevenlabs/turbo-v2
text-to-audio

text-to-audio

ElevenLabs Turbo V2 | Text To Speech | $0.1 Per 1K Characters | WaveSpeedAI

elevenlabs/turbo-v2

ElevenLabs Turbo V2 is a Text-To-Speech model available via WaveSpeedAI, billed at $0.05 per 1000 characters for API requests. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

This parameter supports English text normalization, which improves performance in number-reading scenarios.

Idle

Your request will cost $0.05 per run.

For $1 you can run this model approximately 20 times.

ExamplesView all

README

ElevenLabs — Turbo V2 Text-to-Speech

Turbo V2 turns written text into natural-sounding speech with clear pronunciation, smooth pacing, and expressive tone—ideal for voiceovers, narration, tutorials, podcasts, and digital content. It supports a rich library of multi-lingual voices and fast turnaround for production workflows. See the list here.

Key Features

  • Fast, expressive synthesis with humanlike prosody
  • Multi-language support and robust English number/date reading
  • Fine control via similarity and stability sliders
  • Speaker Boost for crisper English numerals, times, and measurements
  • Works with built-in voices and your custom voice IDs

Pricing

  • $0.05 per 1,000 characters
  • If the input length is less than 1000 characters, it will be counted as 1000 characters to pay.

How to Use

  1. Enter your script in the text field.
  2. Set voice_id to a built-in or custom voice (for example: Gigi, Callum, Alice). See the full catalog in the voice list.
  3. Optional controls • similarity: 0–1 (higher = closer to the base voice timbre) • stability: 0–1 (higher = more consistent delivery) • use_speaker_boost: improves English number and unit reading
  4. Run to synthesize and preview your audio.

Notes

  • For the best rhythm, use clear punctuation and split very long text into smaller chunks.
  • voice_id must be valid; if you see a voice-ID error, pick one from the official list above.