infery
← All models

Personaplex

personaplex-realtime

Text to Speechby Personaplex

PersonaPlex is a real-time, full-duplex speech-to-speech conversational model that enables persona control through text-based role prompts and audio-based voice conditioning.

Details

Accepts
audio

Pricing

Price
0.125 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedRandom seed for reproducibility.
audiorequiredstringInput audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.
voicestringenum: NATF0, NATF1, NATF2, NATF3, NATM0, NATM1Voice ID for the AI response. NAT = natural, VAR = variety. F = female, M = male. Ignored when voice_audio_url is provided.
promptstringText prompt describing the AI persona and conversation context.
top_k_textintegerTop-K sampling for text tokens.
top_k_audiointegerTop-K sampling for audio tokens.
voice_audio_urlURL to a voice sample audio for on-the-fly voice cloning. When provided, the AI responds in the cloned voice instead of the preset 'voice'. 10+ seconds of clear speech recommended. Billed at 2x rate.
temperature_textnumberText sampling temperature. Higher values produce more diverse outputs.
temperature_audionumberAudio sampling temperature. Higher values produce more diverse outputs.

Output

FieldTypeDescription
textstringGenerated text tokens for this chunk.
audiostringGenerated audio chunk (PCM s16le, 24kHz mono). Base64-encoded in JSON transport.