Eleven V4 Turbo Text-to-Speech converts text into expressive multilingual speech with configurable voice selection, stability, and similarity controls for narration, dialogue, localization, virtual assistants, and scalable voice production workflows.
Every plan, free included. Runs spend your account’s credits.
Example outputThe smallest request that works: the required fields only.
Percify APIcurl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "eleven-v4-turbo",
"input": {
"text": "Hello from the Percify API.",
"voice_id": "Alicia"
}
}'4 fields in input, required first.
textRequiredText to convert to speech. Supports expressive audio tags such as [whispering] and [laughing]. Maximum 10,000 characters for this endpoint.
voice_idRequiredThe voice to use for speech generation. Choose a preset voice name, or enter any ElevenLabs voice ID.
stabilityOptionalHow consistent the delivery stays. Lower values allow more expressive variation; higher values favor consistency.
similarityOptionalHow closely the generated speech follows the selected voice. Higher values increase voice similarity.
$0.24 / minElevenLabs Audio Isolation isolates speech from background noise to produce clearer dialogue, interviews, voice recordings, podcasts, and other speech-focused audio workflows.
$0.16 / 1kEleven V4 Text-to-Speech converts text into expressive multilingual speech with configurable voice selection, stability, and similarity controls for narration, dialogue, localization, virtual assistants, and voice production workflows.
$0.10 / 1kGemini 3.8 Flash Text-to-Speech generates expressive speech from text with configurable voice and delivery-style controls for narration, dialogue, localization, virtual assistants, and voice production workflows.
$0.10 / 1kNatural speech with expressive delivery.
Pick a use case, run it in the playground, copy the call.
Every plan, free included. Runs spend your account’s credits.