Skip to content

Text to speech (ElevenLabs) API

6 endpoints on fal.ai, from $0.04 per 1,000 characters.

Versions

Per 1,000 characters

Inputs

Text
The text to convert to speech
Inputs
A list of dialogue inputs, each containing text and a voice ID which will be converted into speech
Language code
Language code (ISO 639-1) used to enforce a language for the model. Optional
Stability
Voice stability (0-1). Optional
Apply text normalization
This parameter controls text normalization with three modes: 'auto', 'on', and 'off' (auto, on or off). Optional
Timestamps
Whether to return timestamps for each word in the generated speech. Optional
Voice
The voice to use for speech generation. Optional
Similarity boost
How closely the output follows the reference voice. Optional
Seed
Random seed for reproducibility. Optional
Output format
Output format of the generated audio. Optional

Other audio models

Lowest price

Questions

Which Text to speech (ElevenLabs) versions can my agent run?

ElevenLabs Eleven v3 expressive text to speech, ElevenLabs Eleven v3 multi-speaker dialogue to speech text, ElevenLabs Eleven v4 expressive text to speech, ElevenLabs Eleven v4 Turbo fast text to speech, ElevenLabs Multilingual v2 text to speech and ElevenLabs Turbo v2.5 fast text to speech.

How is it billed?

Per call, at the provider's price with no markup, from $0.04 per 1,000 characters. Your agent sees the price before it runs a tool.

Connect your agent to 2,400+ tools for free

Sign in with Google or GitHub. No card required.