silk mulberry 1.5

​

well supported for

• language: hindi in devanagari plus english in latin (code-mixed).
• voice control: natural-language descriptions across age, accent, pitch, timbre, pacing, emotion, and register — plus four preset studio voices.
• accents: global (american, british, indian, …) and indian regional (hindi, punjabi, bengali, south indian, …).
• content: low-latency synthesis for narration, voice agents, and creative or stylized voices.

​

how it works

• description: write the voice in natural language (age, accent, pitch, timbre, pacing, emotion).
• preset voices: set speaker to speaker_1…speaker_4, and shift pitch with f0_up_key.
• script: write hindi words in devanagari and english words in latin, e.g. आज का episode थोड़ा अलग है.

​

preset voices

​

example request

curl -X POST https://silk-api.rumik.ai/v1/tts \
  -H "Authorization: Bearer rk_live_•••••••••" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mulberry",
    "text": "Welcome to the future of synthetic speech.",
    "description": "warm, upbeat narrator",
    "speaker": "speaker_2",
    "f0_up_key": 0
  }' \
  --output mulberry.wav

​

parameters