infery
← All models

Maya1

maya

Text to Speechby Maya

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

Details

Accepts
text

Pricing

Price
0.250 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
textrequiredstringThe text to synthesize into speech. You can embed emotion tags anywhere in the text using the format <emotion_name>. Available emotions: laugh, laugh_harder, sigh, chuckle, gasp, angry, excited, whisper, cry, scream, sing, snort, exhale, gulp, giggle, sarcastic, curious. Example: 'Hello world! <exci…
top_pnumberNucleus sampling parameter. Controls diversity of token selection.
promptrequiredstringDescription of the voice/character. Includes attributes like age, accent, pitch, timbre, pacing, tone, and intensity. See examples for format.
max_tokensintegerMaximum number of SNAC tokens to generate (7 tokens per frame). Controls maximum audio length.
sample_ratestringenum: 48 kHz, 24 kHzOutput audio sample rate. 48 kHz provides higher quality audio, 24 kHz is faster.
temperaturenumberSampling temperature. Lower values (0.2-0.5) produce more stable/consistent audio. Higher values add variation.
output_formatstringenum: wav, mp3Output audio format for the generated speech
repetition_penaltynumberPenalty for repeating tokens. Higher values reduce repetition artifacts.

Output

FieldTypeDescription
rtfnumberReal-time factor (generation_time / audio_duration). Lower is better.
audioThe generated audio file containing the speech (WAV or MP3 format, 24kHz or 48kHz mono depending on upsampler)
durationnumberDuration of the generated audio in seconds
sample_ratestringSample rate of the generated audio
generation_timenumberTime taken to generate the audio in seconds