WaveSpeedText to speechComing soon

wavespeed-ai/omnivoice/voice-clone

Name: wavespeed-ai/omnivoice/voice-clone
Brand: WaveSpeed

wavespeed-ai/omnivoice/voice-clone is a text to speech tool from WaveSpeed that runs in the background and returns audio. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: audio
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`text` required	text	—	The text content to convert into speech using the cloned voice.
`audio` required	URL or file	—	URL of the reference audio to clone the voice from (3-10 seconds recommended).
`speed`	number 0.1 to 5	1	Playback speed factor. 1.0 = normal speed. Values > 1.0 are faster, < 1.0 are slower.
`reference_text`	text	—	Transcript of the reference audio (optional, improves accuracy).

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "wavespeed",
    "model": "wavespeed-ai/omnivoice/voice-clone",
    "input": {
      "text": "<text>",
      "audio": "<audio>"
    }
  }'