Seed Audio 1.0 generates natural speech and audio from a prompt, with optional voice, reference audio, or reference image guidance.
Percify APIseed-audio-1API 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": "seed-audio-1",
"input": {
"prompt": "A red fox running through fresh snow at sunrise"
}
}'8 fields in input, required first.
promptRequiredText or audio prompt to synthesize. Reference uploaded audio clips in the prompt as @Audio1, @Audio2, or @Audio3.
imageOptionalOptional single reference image URL. Do not use together with audio.
pitchOptionalPitch shift in semitones.
speedOptionalSpeech speed multiplier.
audiosOptionalOptional reference audio URLs. Upload up to 3 clips and reference them in the prompt as @Audio1, @Audio2, or @Audio3. Do not use together with image.
volumeOptionalSpeech volume multiplier.
sample_rateOptionalOutput sample rate in Hz.
output_formatOptionalAudio output format.
$0.225ElevenLabs Music generates original songs from text descriptions.
$0.20Google Lyria 3 Pro generates high-quality music tracks from text prompts and optional image input.
$0.125mureka ai / mureka v9 / generate song via Mureka official API.
$0.375Music 2.6 generates complete songs with vocals and instrumentals from text prompts and lyrics.
Pick a use case, run it in the playground, copy the call.
API keys come with the Scale and Ultra plans