ElevenLabsThe Voice of AI
One of the most natural-sounding AI voice models. Text-to-speech, music generation, dubbing, and transcription, all through a single serverless API.
The full audio AI suite
Speech synthesis, music generation, transcription, voice changing, and dubbing. Every endpoint pay-per-use with no minimums.
Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!
Generate high quality, realistic music with fine controls using Elevenlabs Music!
Generate text from speech using ElevenLabs advanced speech-to-text model.
Generate realistic audio dialogues using Eleven-v3 from ElevenLabs.
Generate text-to-speech audio using Eleven-v3 from ElevenLabs.
Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.
Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.
Change the voices in your audios with voices in ElevenLabs!
Generate dubbed videos or audios using ElevenLabs Dubbing feature!
One API. Every Audio Modality.
Voices That Sound Human
Eleven V3 produces speech with natural intonation, emotional nuance, and accurate pacing. Over 20 built-in voices across narration, conversational, character, and broadcast styles. Turbo v2.5 delivers under 75ms latency for real-time applications.
Studio-Quality Audio from Text
Generate full music tracks in any genre from a text description. Control structure with section prompts, choose vocal or instrumental mode, and export in 19 formats.
99-Language Transcription
Scribe v2 transcribes audio in 99 languages with word-level timestamps, speaker diarization, and audio event detection. At $0.008 per minute, it is one of the most cost-effective transcription APIs available.
Hear what ElevenLabs can create
Hit play on any example below, then copy the prompt and try it yourself in the TTS or Music playground.
"The old lighthouse keeper adjusted his glasses and peered through the storm. 'Thirty years,' he muttered, 'and the sea still finds new ways to surprise me.'"
"Lo-fi jazz hip-hop with a dusty vinyl crackle, mellow Rhodes piano chords, a slow boom-bap drum pattern, and a wandering saxophone melody that feels like 2am in a coffee shop"
"Breaking news update: financial markets responded positively to the announcement, with major indices climbing throughout the afternoon session. Analysts expect continued momentum into next week."
"Dark cinematic trailer music with deep brass stabs, thunderous taiko drums, a rising tension string ostinato, and a massive sub-bass drop that hits like a shockwave"
A few lines of code.
Lifelike audio.
fal.ai handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPUs to manage.
- Serverless: scales to zero, scales to millions
- Pay per use, no minimums
- Python and JavaScript SDKs, plus REST API
import fal_client
result = fal_client.run(
"fal-ai/elevenlabs/tts/eleven-v3",
arguments={
"text": "Hello from fal.ai!",
"voice": "Sarah",
}
)
# result.audio.url → your generated audioCommon questions about ElevenLabs
What ElevenLabs models are available on fal.ai?
fal.ai offers the full ElevenLabs audio suite: Eleven V3 (latest TTS), Turbo v2.5 (low-latency TTS), Multilingual v2 (29 languages), text-to-dialogue, music generation, speech-to-text (Scribe v1 & v2), voice changer, and dubbing.
How natural does the text-to-speech sound?
ElevenLabs is widely regarded as the most natural-sounding AI voice platform. Eleven V3, their latest model, produces speech with nuanced intonation, emotional awareness, and natural pacing. It supports over 20 built-in voices across different styles: narration, conversational, characters, and broadcast.
What languages are supported?
Multilingual v2 supports 29 languages with high accent accuracy. Turbo v2.5 supports 32 languages with the lowest latency. Scribe v2 transcribes 99 languages. Dubbing auto-translates audio into Spanish, French, German, Japanese, Portuguese, and Chinese.
Can I generate music?
Yes. ElevenLabs Music generates studio-quality tracks from text prompts in any genre. It supports both vocal and instrumental modes, section control for structuring compositions, and 19 output formats. Pricing is $0.80 per minute of generated audio.
How much does ElevenLabs cost on fal.ai?
TTS: $0.10 per 1,000 characters (Eleven V3, Multilingual v2) or $0.05 per 1,000 characters (Turbo v2.5). Speech-to-text: $0.008/min (Scribe v2) or $0.03/min (Scribe v1). Music: $0.80/min. Voice changer: $0.30/min. Dubbing: $0.90/min. Pay-per-use with no minimums.
How do I get started with the API?
Install the fal.ai SDK (Python or JavaScript), grab an API key from your dashboard, and make your first request in a few lines of code. The API is serverless, so no infrastructure to set up. Check the API documentation for all available parameters and voice options.
Can I use ElevenLabs for commercial projects?
Yes. Content generated through the fal.ai API can be used in commercial projects. Check fal.ai's terms of service for full details on usage rights and licensing.
Ready to build with voice?
Start generating lifelike audio with ElevenLabs on fal.ai.