Omnivoice Text To Speech API Documentation

Omnivoice Text To Speech API Documentation

Playground

OmniVoice is a massively multilingual zero-shot TTS supporting 600+ languages. Generate speech with auto voice or design custom voices using natural language descriptions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

OmniVoice Text-to-Speech converts any text into natural, expressive speech in 600+ languages. Choose from a set of voice attributes — gender, age, pitch, accent — and the model generates matching audio in seconds. No voice sample needed.

Why Choose This?

• Attribute-driven voice design Pick from predefined voice attributes (gender, age, pitch, accent) to create your ideal voice — no audio sample required.

• 600+ languages The broadest language coverage among zero-shot TTS models.

• Speed control Adjust the speaking rate to match your content pacing needs.

• Fast generation Output delivered in under 5 seconds.

Parameters

Valid Voice Attributes

Combine any of these with commas (e.g. female, low pitch, british accent):

Gender: female, male

Age: child, teenager, young adult, middle-aged, elderly

Pitch: very low pitch, low pitch, moderate pitch, high pitch, very high pitch

Style: whisper

Accent: american accent, australian accent, british accent, canadian accent, chinese accent, indian accent, japanese accent, korean accent, portuguese accent, russian accent

Examples

• female, low pitch, british accent
• male, young adult, american accent
• female, elderly, whisper
• male, high pitch, indian accent

How to Use

1. Enter your text — type or paste the content you want spoken.
2. Choose voice attributes (optional) — combine gender, age, pitch, and accent attributes separated by commas.
3. Set speed (optional) — adjust the speaking rate if needed.
4. Submit — generate and download your audio in seconds.

Pricing

Best Use Cases

• Content creation — Generate voiceovers for videos, ads, and social media.
• Audiobook & podcast production — Convert written content into listenable audio at scale.
• App & product demos — Add natural speech to prototypes and presentations.
• Accessibility — Convert text content into audio for audio-first audiences.
• Multilingual apps — Generate speech in 600+ languages from a single model.

Pro Tips

• Combine 2–3 attributes for best results (e.g. female, young adult, british accent).
• Omit voice_description entirely for a random voice — useful for variety in batch generation.
• Use whisper for ASMR-style or intimate content.
• Adjust speed to 0.8 for calm narration or 1.3 for energetic delivery.

Related Models

• OmniVoice Voice Clone — Clone a specific voice from a reference audio sample.

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",
  "speed": 1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/omnivoice/text-to-speech" \
  -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