kwaivgi/kling-tts
Kling Tts is KwaiVGI's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runkwaivgi/kling-ttsInput Schema
3 parameters · 0 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Optional | The text to be converted to speech · Max length: 500 |
voice_id | string | Optional | The voice ID to use for speech synthesis · Options: genshin_vindi2, zhinen_xuesheng, AOT, ai_shatang, genshin_klee2, genshin_kirara, ai_kaiya, oversea_male1, ai_chenjiahao_712, girlfriend_4_speech02, chat1_female_new-3, chat_0407_5-1, cartoon-boy-07, uk_boy1, cartoon-girl-01, PeppaPig_platform, ai_huangzhong_712, ai_huangyaoshi_712, ai_laoguowang_712, chengshu_jiejie, you_pingjing, calm_story1, uk_man2, laopopo_speech02, heainainai_speech02, reader_en_m-v1, commercial_lady_en_f-v1, tiyuxi_xuedi, tiexin_nanyou, girlfriend_1_speech02, girlfriend_2_speech02, zhuxi_speech02, uk_oldman3, dongbeilaotie_speech02, chongqingxiaohuo_speech02, chuanmeizi_speech02, chaoshandashu_speech02, ai_taiwan_man2_speech02, xianzhanggui_speech02, tianjinjiejie_speech02, diyinnansang_DB_CN_M_04-v2, yizhipiannan-v1, guanxiaofang-v2, tianmeixuemei-v1, daopianyansang-v1, mengwa-v1 · Default: "genshin_vindi2" genshin_vindi2zhinen_xueshengAOTai_shatanggenshin_klee2genshin_kiraraai_kaiyaoversea_male1ai_chenjiahao_712girlfriend_4_speech02chat1_female_new-3chat_0407_5-1cartoon-boy-07uk_boy1cartoon-girl-01PeppaPig_platformai_huangzhong_712ai_huangyaoshi_712ai_laoguowang_712chengshu_jiejieyou_pingjingcalm_story1uk_man2laopopo_speech02heainainai_speech02reader_en_m-v1commercial_lady_en_f-v1tiyuxi_xueditiexin_nanyougirlfriend_1_speech02girlfriend_2_speech02zhuxi_speech02uk_oldman3dongbeilaotie_speech02chongqingxiaohuo_speech02chuanmeizi_speech02chaoshandashu_speech02ai_taiwan_man2_speech02xianzhanggui_speech02tianjinjiejie_speech02diyinnansang_DB_CN_M_04-v2yizhipiannan-v1guanxiaofang-v2tianmeixuemei-v1daopianyansang-v1mengwa-v1 |
voice_speed | number | Optional | Rate of speech · Min: 0.8 · Max: 2 · Default: 1 |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kwaivgi/kling-tts",
"text": "Hello world! Kling TTS is available on FAL!",
"voice_id": "genshin_vindi2",
"voice_speed": 1,
"prompt": "a beautiful sunset over mountains"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling TTS
Kling TTS converts a short written passage into synthesized speech. The endpoint pairs a text field of up to 500 characters with a catalog of 46 voice IDs, making voice selection a deliberate part of each request.
Speech pace remains adjustable after the voice is chosen: the supported range runs from 0.8× to 2×, with 1× as the default. The asynchronous result is delivered as a downloadable audio file, suitable for brief spoken lines and voiceover segments.
Highlights
Forty-six voice choices. Select from a broad enumerated voice catalog instead of relying on one fixed narrator.
Pace control. Set speech speed anywhere from 0.8× to 2×, with natural-speed 1× as the starting value.
Concise script input. Each synthesis request accepts up to 500 characters of text.
Audio-file delivery. The generated speech arrives through a downloadable media URL.
Pricing
| Billing unit | Price |
|---|---|
| Per request | $0.007 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For speech synthesis, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"text": "Hello world! Kling TTS is available on FAL!"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | kwaivgi/kling-tts |
| Inputs | text, voice_id, voice_speed |
| Required inputs | None |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |