Where do I find a voice ID?

Open the voice in your ElevenLabs VoiceLab or the Voices page; the voice ID is in the URL and on the voice's details. Paste that 20-character ID here. A default Rachel ID is pre-filled as a starting point.

What do stability and similarity boost do?

Stability controls how consistent the voice is — higher is steadier but flatter, lower is more expressive but variable. Similarity boost pushes the output toward the original voice's timbre. Style adds exaggeration on supported models.

How is usage charged?

ElevenLabs bills credits per character of input text, with your plan setting the monthly quota. The playground shows the character count so you can gauge usage before generating; the exact credit conversion depends on your plan and model.

No. The audio is held only in your browser as a temporary object URL and your API key is never persisted. The request goes directly from your browser to the ElevenLabs API.

ElevenLabs API Playground

ElevenLabs API playground

This tool calls the ElevenLabs text-to-speech API directly from your browser with your own key, so you can audition voices and fine-tune voice settings on real text without code. Paste a voice ID, adjust stability, similarity boost, and style, and generate — the MP3 plays inline and downloads with one click.

How it works

On generate, the playground POSTs to https://api.elevenlabs.io/v1/text-to-speech/{voiceId} with an xi-api-key header, your text, and a voice_settings object carrying stability, similarity boost, and style. ElevenLabs streams back MP3 audio; the browser wraps the bytes in an object URL for an inline player and download link. There is no backend and nothing is stored.

Tips and notes

Tune stability per use. Audiobooks want higher stability for consistency; characters and ads benefit from lower stability and more style.
Similarity boost ≠ stability. Boost pulls toward the source timbre; raise it if the clone sounds generic, lower it if it sounds strained.
Keep text natural. ElevenLabs reads punctuation and casing as performance cues — write the way it should be spoken.
Watch the character count. Usage is per character, so trimming reduces both cost and generation time.