ReplicateText to speechComing soon

elevenlabs/v3

Name: elevenlabs/v3
Brand: Replicate

elevenlabs/v3 is a text to speech tool from Replicate 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.

Priced by usage

Pricing

$0.13 per 1,000 characters of prompt.

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
`prompt` required	text	—	The text to convert to speech
`speed`	number 0.7 to 1.2	1	Speed of speech (0.25 to 4.0)
`style`	number 0 to 1	0	Style exaggeration (0.0 to 1.0)
`voice`	JSON	Rachel	Voice choice for speech generation
`next_text`	text		Next text for context
`stability`	number 0 to 1	0.5	Stability setting for voice generation (0.0 to 1.0)
`language_code`	text	en	Language code (e.g., 'en', 'es', 'fr')
`previous_text`	text		Previous text for context
`similarity_boost`	number 0 to 1	0.75	Similarity boost setting (0.0 to 1.0)

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": "replicate",
    "model": "elevenlabs/v3",
    "input": {
      "prompt": "<prompt>"
    }
  }'