Streaming text to speech

Convert text to speech with real-time streaming audio delivery.

Key Features:

• Low-latency audio streaming - playback can start immediately as chunks arrive
• Automatic language detection
• Multiple format support: MP3 or PCM/WAV
• High-quality audio: 24kHz sample rate, 16-bit mono

Request Body:

• text: Input text to convert to speech - required
• language: Language code (default: “auto”) - “auto” for automatic detection, or ISO 639-1 codes: en, zh, hi, es, ar, bn, pt, ru, ja, pa, de, ko, fr, tr, it, th, pl, nl, id, vi, ur
• format: Audio format (default: “mp3”) - “mp3” for compressed MPEG audio (96 kbps) or “pcm” for uncompressed WAV
• model: TTS model identifier (default: “auto”) - “auto” selects the default provider; a registry-resolvable id dispatches to the matching provider (note: not all providers support format: "mp3")

Response:

• Streams audio chunks in real-time
• Returns X-Language-Code header with detected/used language
• Content-Type: audio/mpeg (MP3) or audio/wav (PCM)

Use Cases:

• Real-time applications requiring immediate audio playback
• Interactive voice responses
• Low-latency text-to-speech scenarios

POST /api/v1/llm/speech/tts/stream

Python (SDK)

Python

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", model="auto", format_="mp3")

    # Handle response
    print(res)

200

"(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>.

Headers

X-On-Behalf-Of · string

Optional external end-user identifier forwarded by the API gateway.

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

model · string · default: auto

TTS model identifier. Defaults to 'auto', which selects the default provider. Registry-resolvable ids dispatch to the matching provider.

Example:

"auto"

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

200

audio/mpeg

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