ElevenAPI
Production-grade voice AI in a few lines of code
Production-grade voice AI in a few lines of code
Production-grade voice AI in a few lines of code
Get your ElevenLabs API key, see transparent API pricing, and make your first call in minutes. Powering text-to-speech, voice, speech-to-text, and more behind one key at leading Fortune 500s.
10K free credits per month
Full access to all APIs
SOC 2 Type 2 and ISO 27001
Voices that sound natural and emotionally rich, backed by an API that’s solid and dependable. Made it possible to scale new languages and markets with confidence.
Voices that sound natural and emotionally rich, backed by an API that’s solid and dependable. Made it possible to scale new languages and markets with confidence.
Cankut Kostur
Sr. Engineer, Codeway
from elevenlabs import ElevenLabs client = ElevenLabs(api_key="sk_...") audio = client.text_to_speech.convert( voice_id="U1me6X0sIhQz6nAjDuVU", model_id="eleven_flash_v2_5", text="Your platform just found its voice.", ) # streamed audio, ~75 ms to first byte
$ curl -X POST https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb \ -H "xi-api-key: $ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "Your platform just found its voice.", "model_id": "eleven_flash_v2_5" }' --output speech.mp3
$ elevenlabs text-to-speech convert \ --model-id eleven_flash_v2_5 \ --voice-id 3cjtcbSfNCiKYL34TDbF \ --text "Your platform just found its voice." \ --output speech.mp3 # npm i -g @elevenlabs/cli — one command from prompt to audio
import { ElevenLabsClient } from "elevenlabs"; const client = new ElevenLabsClient({ apiKey: process.env.ELEVENLABS_API_KEY! }); const audio = await client.textToSpeech.convert("6ce2j5ZU8hRGBD9VwEaX", { text: "Your platform just found its voice.", modelId: "eleven_flash_v2_5", }); // fully typed, edge-ready
from elevenlabs import ElevenLabs client = ElevenLabs(api_key="sk_...") audio = client.text_to_speech.convert( voice_id="U1me6X0sIhQz6nAjDuVU", model_id="eleven_flash_v2_5", text="Your platform just found its voice.", ) # streamed audio, ~75 ms to first byte
$ curl -X POST https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb \ -H "xi-api-key: $ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "Your platform just found its voice.", "model_id": "eleven_flash_v2_5" }' --output speech.mp3
$ elevenlabs text-to-speech convert \ --model-id eleven_flash_v2_5 \ --voice-id 3cjtcbSfNCiKYL34TDbF \ --text "Your platform just found its voice." \ --output speech.mp3 # npm i -g @elevenlabs/cli — one command from prompt to audio
import { ElevenLabsClient } from "elevenlabs"; const client = new ElevenLabsClient({ apiKey: process.env.ELEVENLABS_API_KEY! }); const audio = await client.textToSpeech.convert("6ce2j5ZU8hRGBD9VwEaX", { text: "Your platform just found its voice.", modelId: "eleven_flash_v2_5", }); // fully typed, edge-ready
from elevenlabs import ElevenLabs client = ElevenLabs(api_key="sk_...") audio = client.text_to_speech.convert( voice_id="U1me6X0sIhQz6nAjDuVU", model_id="eleven_flash_v2_5", text="Your platform just found its voice.", ) # streamed audio, ~75 ms to first byte
$ curl -X POST https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb \ -H "xi-api-key: $ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "Your platform just found its voice.", "model_id": "eleven_flash_v2_5" }' --output speech.mp3
$ elevenlabs text-to-speech convert \ --model-id eleven_flash_v2_5 \ --voice-id 3cjtcbSfNCiKYL34TDbF \ --text "Your platform just found its voice." \ --output speech.mp3 # npm i -g @elevenlabs/cli — one command from prompt to audio
import { ElevenLabsClient } from "elevenlabs"; const client = new ElevenLabsClient({ apiKey: process.env.ELEVENLABS_API_KEY! }); const audio = await client.textToSpeech.convert("6ce2j5ZU8hRGBD9VwEaX", { text: "Your platform just found its voice.", modelId: "eleven_flash_v2_5", }); // fully typed, edge-ready
Voices that sound natural and emotionally rich, backed by an API that’s solid and dependable. Made it possible to scale new languages and markets with confidence.
Cankut Kostur
Sr. Engineer, Codeway
Hear the result
Generate first audio in ~75ms with Flash
Trusted by 7.5M+
No credit card required