Kuaishou: Kling TTS

Generate speech from text prompts and different voices using the Kling TTS model, which leverages advanced AI techniques to create high-quality text-to-speech.

Compare models

kling-tts

AvailableKuaishouText to speechSync

Price: From $0.007
Modalities: Audio

About Kling TTS

Kling TTS is Kuaishou's text-to-speech model. It converts text prompts into spoken audio and lets you choose between different voices. It sits beside the Kling video models, so narration for a Kling clip can come from the same maker. It takes text as input and returns audio.

Where it works well

Converts written text into speech with a choice of voices.
Comes from the same maker as the Kling video line, which keeps a narration-plus-video workflow in one family.
Simple speech-only operation, without music or sound-effect features to configure.
Per-request use suits short lines such as captions, prompts and voiceovers.

When to choose another model

It offers no voice cloning or emotion controls, so specialist speech models fit expressive work better.
It outputs audio only; any lip-synced video needs a separate model such as Kling AI Avatar.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Text to speechTokenLab endpoint

POST/v1/audio/speech

curl -X POST "https://api.tokenlab.sh/v1/audio/speech" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "operation": "tts",
  "model": "kling-tts",
  "input": "Hello from TokenLab.",
  "voice": "alloy"
}'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text to speech

per request

Official price: $0.007
Verified price: —
Discount: —

	Official priceper request	Verified priceper request	Discount
Text to speech	$0.007	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 21, 2026, 12:50 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Kling TTS in Console with a prompt ready to edit or send.

Help me try kling-tts with a short audio request at /v1/audio/speech. Show the result and cost.

Use cases

Clip narration
Voice a short script to lay under a generated Kling video, so narration and picture come from one maker.
Avatar audio source
Create the speech track that a Kling AI Avatar model then animates a character to.
Prompt audio
Read interface messages, notifications and help text aloud for an app or a kiosk without recording each line.

Prompt examples

Welcome back. Your order has shipped and should arrive on Thursday.

In the next ten minutes, we will build a small web app, one step at a time.

Attention passengers: the train to the airport departs from platform four.

FAQ

What does Kling TTS do?

It generates speech from text. You send the text and pick a voice, and the model returns an audio file you can use in a video or app.

Can I choose different voices?

Yes, Kling TTS supports different voices in addition to text prompts. You choose the voice in the request, so one script can be voiced several ways for different characters.

Can it clone my voice?

No. It is plain text-to-speech with no cloning feature. Use a speech model that advertises voice cloning if you need to match the voice of a specific person.

Can I pair it with Kling avatars?

Yes. Audio from Kling TTS can serve as the input to Kling AI Avatar Standard or Pro, which animate a character speaking it. The avatar model handles the face and lip movement, while this model supplies only the voice track.

How much does Kling TTS cost?

On TokenLab, Kling TTS costs $0.007 per request. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Kling TTS use?

Use https://api.tokenlab.sh/v1/audio/speech for Kling TTS. The request example below shows the matching code shape.

Which operations does Kling TTS support?

Kling TTS supports Text to speech. Select an operation above to see its endpoint and request example.