Elevenlabs Eleven V3 API Documentation

Elevenlabs Eleven V3 API Documentation

Playground

ElevenLabs eleven-v3 is a text-to-speech model available as a hosted endpoint; requests cost $0.1 per 1000 characters. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Eleven V3 converts written text into natural, expressive speech using ElevenLabs’ advanced deep-learning speech synthesis technology. It delivers clear pronunciation, smooth pacing, and lifelike emotion — ideal for voiceovers, narrations, podcasts, and digital content.

🎧 Key Features

• High Naturalness — produces human-like intonation, timing, and articulation.
• Multi-Language Support — generate voices in multiple global languages with automatic accent adaptation.
• Customizable Parameters — control tone and realism via similarity and stability settings.
• Speaker Boost — enhances clarity for English numerals, times, and measurements.
• Wide Voice Library — choose from a rich set of built-in voices (see voice list here).

💰 Pricing

Billed by the exact character count of the input text, prorated — no rounding up to 1,000.

• Rate: $0.20 per 1,000 characters ($200 per 1M characters)
• No minimum charge; a 100-character request costs $0.020

🚀 How to Use

1. Enter your text in the text field (up to 5,000 characters).
2. Select a voice from the voice_id dropdown (e.g., Alice, Elli, George).
3. Adjust optional parameters:

• similarity: 0–1 (higher = closer to base voice tone)
• stability: 0–1 (higher = consistent delivery)
• use_speaker_boost: enhances number reading in English.

4. Click Run to generate and preview your audio.

📝 Notes

• Audio output is returned in MP3 format.
• Works best for English, but supports multiple languages.
• Long texts may require splitting for stable generation.
• Ensure text avoids ambiguous punctuation for optimal rhythm and tone.
• If the model returns an error message like incorrect voice ID, please modify the code according to the table mentioned earlier voice list here.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "text": "A clear example input",
  "voice_id": "Alice",
  "similarity": 1,
  "stability": 0.5,
  "use_speaker_boost": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/elevenlabs/eleven-v3" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters