POST
/
api
/
v1
/
language_groups
/
voices
/
sample
Python (SDK)
import os
from syllable_sdk import SyllableSDK, models


with SyllableSDK(
    api_key_header=os.getenv("SYLLABLESDK_API_KEY_HEADER", ""),
) as ss_client:

    res = ss_client.language_groups.language_groups_create_voice_sample(request={
        "language_code": models.LanguageCode.ES_US,
        "voice_provider": models.TtsProvider.GOOGLE,
        "voice_display_name": models.AgentVoiceDisplayName.EN_US_NEURAL2_D,
        "voice_speed": 1,
        "voice_pitch": 0,
    })

    # Handle response
    print(res)
This response does not have an example.

Authorizations

Syllable-API-Key
string
header
required

Body

application/json

Request model to generate a sample audio file for a given voice and language.

language_code
enum<string>
required

BCP 47 code of the language

Available options:
yue-HK,
en-US,
ko-KR,
zh-CN,
fa-IR,
es-US,
th-TH,
vi-VN,
bs-BA,
sw-KE
voice_provider
enum<string>
required

TTS provider of the voice to use for the language

Available options:
OpenAI,
ElevenLabs,
Google
voice_display_name
enum<string>
required

Display name of the voice to use for the language

Available options:
Achernar (English),
Achernar (Korean),
Achernar (Mandarin),
Achernar (Spanish),
Achernar (Thai),
Achernar (Vietnamese),
Alice,
Alloy,
Aoede (English),
Aoede (Korean),
Aoede (Mandarin),
Aoede (Spanish),
Aoede (Thai),
Aoede (Vietnamese),
Ash,
Bill,
Brian,
Callirrhoe (English),
Callirrhoe (Korean),
Callirrhoe (Mandarin),
Callirrhoe (Spanish),
Callirrhoe (Thai),
Callirrhoe (Vietnamese),
Callum,
Charlie,
Charlotte,
Charon (English),
Charon (Korean),
Charon (Mandarin),
Charon (Spanish),
Charon (Thai),
Charon (Vietnamese),
Chris,
cmn-TW-Wavenet-A,
Coral,
Daniel,
Echo,
en-US-Neural2-D,
en-US-Neural2-F,
en-US-Neural2-J,
en-US-Studio-O,
Eric,
es-US-Neural2-A,
es-US-Neural2-B,
Fable,
Fenrir (English),
Fenrir (Korean),
Fenrir (Mandarin),
Fenrir (Spanish),
Fenrir (Thai),
Fenrir (Vietnamese),
George,
Jessica,
ko-KR-Neural2-A,
Kore (English),
Kore (Korean),
Kore (Mandarin),
Kore (Spanish),
Kore (Thai),
Kore (Vietnamese),
Laura,
Leda (English),
Leda (Korean),
Leda (Mandarin),
Leda (Spanish),
Leda (Thai),
Leda (Vietnamese),
Liam,
Lily,
Matilda,
Nova,
Onyx,
Orus (English),
Orus (Korean),
Orus (Mandarin),
Orus (Spanish),
Orus (Thai),
Orus (Vietnamese),
Puck (English),
Puck (Korean),
Puck (Mandarin),
Puck (Spanish),
Puck (Thai),
Puck (Vietnamese),
River,
Roger,
Sarah,
Sage,
Shimmer,
Umbriel (English),
Umbriel (Korean),
Umbriel (Mandarin),
Umbriel (Spanish),
Umbriel (Thai),
Umbriel (Vietnamese),
Vindemiatrix (English),
Vindemiatrix (Korean),
Vindemiatrix (Mandarin),
Vindemiatrix (Spanish),
Vindemiatrix (Thai),
Vindemiatrix (Vietnamese),
vi-VN-Neural2-A,
Will,
yue-HK-Standard-C,
Zephyr (English),
Zephyr (Korean),
Zephyr (Mandarin),
Zephyr (Spanish),
Zephyr (Thai),
Zephyr (Vietnamese)
voice_speed
number | null

Speed of the voice in the range of 0.25 to 4.0 (OpenAI and Google) or 0.7 to 1.2 (ElevenLabs). Standard speed is 1.0.

Examples:

1

voice_pitch
number | null

Pitch of the voice in the range of -20.0 to 20.0. 20 means increase 20 semitones from the original pitch. -20 means decrease 20 semitones from the original pitch. 0 means use the original pitch. Only supported for Google configs.

Examples:

0

Response

Successful Response

The response is of type file.