ElevenLabs

ElevenLabs is a text-to-speech family known for natural, expressive voices across many languages. Turn any text into lifelike audio.

Best for

Voiceovers, narration and audiobooks.
In-app and assistant voices.
Multilingual speech from a single prompt.


Modality	Audio (text in, speech out)
Example model id	`elevenlabs-v3`
Endpoint	`POST /v1/audio/speech`

Example

curl https://api.heyaskr.ai/v1/audio/speech \
  -H "Authorization: Bearer ASKR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs-v3",
    "voice": "rachel",
    "input": "Crypto in. Intelligence out."
  }' --output speech.mp3

import requests

r = requests.post(
    "https://api.heyaskr.ai/v1/audio/speech",
    headers={"Authorization": "Bearer ASKR_API_KEY"},
    json={
        "model": "elevenlabs-v3",
        "voice": "rachel",
        "input": "Crypto in. Intelligence out.",
    },
)
open("speech.mp3", "wb").write(r.content)
print("Saved speech.mp3")

Pricing

Priced per character of input. As a rough guide, expect around $0.15 per 1,000 characters. Longer text costs proportionally more.

Image
ElevenLabs on Askr: voice picker and waveform

The model id and prices above are examples. Confirm the exact id and current price against the live /v1/models list before you rely on them.

⌘I

Overview

Chat & code

Image

Video

Audio

Best for

Example

Pricing

​Best for

​Example

​Pricing

Best for

Example

Pricing