Skip to main content
POST
/
api
/
v1
/
llm
/
speech
/
tts
/
stream
Python (SDK)
from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.speech.speak_streaming(text="Hello, welcome to our text-to-speech service.", language="en", format_="mp3")

    # Handle response
    print(res)
"(binary)"

Authorizations

​
Authorization
string
header
required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Body

application/json

Request parameters for streaming text-to-speech conversion with language selection and format options.

​
text
string
required

Input text to convert to speech

Minimum string length: 1
​
language
enum<string>
default:auto

Language code: 'auto' for automatic detection, or ISO 639-1 language codes

Available options:
auto,
en,
zh,
hi,
es,
ar,
bn,
pt,
ru,
ja,
pa,
de,
ko,
fr,
tr,
it,
th,
pl,
nl,
id,
vi,
ur
​
format
enum<string>
default:mp3

Audio output format: 'mp3' for MPEG audio (default), or 'pcm' for uncompressed PCM/WAV (24kHz, 16-bit, mono)

Available options:
mp3,
pcm

Response

Streaming audio in MP3 or PCM/WAV format with language code header

MP3 audio stream (when format=mp3): 24kHz sample rate, 96 kbps bitrate, 16-bit, mono