Elevenlabs Voice Changer API Documentation

Elevenlabs Voice Changer API Documentation

Playground

ElevenLabs Voice Changer transforms any audio into speech with a different voice while preserving the original speech patterns and timing. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

ElevenLabs Voice Changer transforms any audio into speech with a different voice. Upload your audio and select a target voice — the model converts the speech while preserving the original timing, emotion, and delivery. Built on ElevenLabs’ industry-leading voice AI with best-in-class quality.

REST inference API, best performance, no cold starts, affordable pricing.

Why Choose This?

• High-quality voice conversion Industry-leading voice transformation that maintains natural speech patterns and emotional delivery.

• Multiple voice options Choose from a variety of pre-built voices to match your content needs (see the voice list).

• Background noise removal Optional noise reduction to clean up audio before conversion.

• Fast processing Optimized for quick turnaround with no cold starts.

• Production-ready API Reliable REST endpoint with predictable per-minute pricing.

Parameters

How to Use

1. Upload your audio — drag and drop, paste a URL, or record directly.
2. Select voice — choose the target voice for conversion.
3. Enable noise removal (optional) — check to clean up background noise.
4. Run — submit and download the converted audio.

Pricing

$0.004 per second of input audio, rounded up to the next whole second.

Billing Rules

• Billed by the duration of the input audio, rounded up to the next second
• Maximum billed duration is 5 minutes, matching the per-request limit
• voice_id and remove_background_noise do not affect pricing

Best Use Cases

• Content Creation — Change voices for podcasts, videos, or audiobooks.
• Dubbing — Convert speech to different voices for localization.
• Privacy — Anonymize voice recordings while preserving content.
• Character Voices — Create distinct character voices for storytelling.
• Accessibility — Convert speech to preferred voice styles.

Pro Tips

• Use clean, high-quality source audio for best results.
• Enable background noise removal if your source has ambient sounds.
• Shorter clips process faster — split long audio for parallel processing.
• Test with different voices to find the best match for your content.

Notes

• Maximum audio duration is 5 minutes per job; longer audio is automatically trimmed to the first 5 minutes.
• For longer content, split into segments and process separately.
• Supported audio formats include MP3, WAV, and other common formats.

Related Models

• ElevenLabs V3 — Generate speech from text with natural-sounding voices.
• OpenAI Whisper — Transcribe audio to text with high accuracy.

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'
{
  "audio": "https://interactive-examples.mdn.mozilla.net/media/cc0-audio/t-rex-roar.mp3",
  "voice_id": "Alicia",
  "remove_background_noise": false
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/elevenlabs/voice-changer" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      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