Natural speech with expressive delivery. Supports two speakers in one take.
Percify APIgemini-ttsThe price changes with the prompt. The estimate call returns the exact figure for your input, free.
API keys come with the Scale and Ultra plans
The smallest request that works: the required fields only.
curl https://api.percify.io/v3/playground/v1/run \
-H "Authorization: Bearer $PERCIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"modelId": "gemini-tts",
"input": {
"prompt": "A red fox running through fresh snow at sunrise"
}
}'4 fields in input, required first.
promptRequiredSupports [sigh], [laughing], [whispering], [short pause].
voiceOptionaloutput_formatOptionalstyle_instructionsOptionalHow it should be read, e.g. "warm, unhurried, like a podcast host".
$0.125The fastest open source TTS model without sacrificing quality.
$0.125Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities.
$0.125Text-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities.
$0.25ElevenLabs eleven-v3 is a text-to-speech model available as a hosted endpoint.
Pick a use case, run it in the playground, copy the call.
API keys come with the Scale and Ultra plans