synthesize speech
synthesize an utterance and return it as a 24 kHz mono WAV file. pass your API key as a bearer token.
Authorizations
your rumik API key, e.g. rk_live_.... create one in the rumik dashboard.
Body
text to synthesize. up to 2000 characters. for muga, prefix with a tone tag, e.g. [happy].
2000"[happy] Namaste! Kaise hain aap?"
which model to use. muga is steered by a tone tag in the text; mulberry is steered by a natural-language description.
muga, mulberry required for mulberry. natural-language voice/style description. the voice is built from this. send it on every mulberry request, including when speaker is set. not used by muga.
"a female 30s hindi voice, smooth timbre, conversational pacing, like a podcast host"
mulberry only. optional named voice. emma, mia, sophia, ava, ira, siya, aisha and zoya are female; lucas, noah, theo and adam are male. case-insensitive. omit and a voice is generated from description. description is required either way.
emma, mia, sophia, ava, ira, siya, aisha, zoya, lucas, noah, theo, adam "siya"
sampling temperature.
nucleus sampling.
top-k sampling.
penalize repeated tokens.
output length cap. for mulberry, if long text comes back truncated, raise this above the default 2048 (up to 8192).
x <= 8192Response
synthesized audio as a 24 kHz mono WAV.
The response is of type file.