Kling TTS

Technical Specifications of kling-tts

What is kling-tts?

kling-tts is a speech synthesis model available through CometAPI for turning text into broadcast-style audio online. It is designed for scenarios where developers or businesses need fast text-to-speech generation with a preview workflow, while also receiving an audio_id that can be used with any Keling API.

This makes kling-tts useful not only for generating playable audio from text, but also for building multi-step voice pipelines where consistent audio asset tracking matters. By combining text-to-broadcast synthesis, preview support, and reusable audio identifiers, the model fits well into content production, narration, and voice-enabled application workflows.

Main features of kling-tts

• Text-to-broadcast audio generation: Converts text input into broadcast-style synthesized audio suitable for narration, announcements, and voice content workflows.
• Preview function: Supports preview-based generation so users can evaluate output before using it in downstream applications or production pipelines.
• Simultaneous audio_id creation: Generates an audio_id alongside the audio output, enabling easier asset management and follow-up operations.
• Keling API compatibility: The generated audio_id can be used with any Keling API, making the model practical for integrated ecosystems and chained workflows.
• API-friendly integration: Designed for programmatic access, allowing developers to embed speech synthesis directly into apps, services, and internal tools.
• Workflow efficiency: Reduces friction in audio generation pipelines by combining synthesis, preview, and reusable identifier output in a single model interaction.

How to access and integrate kling-tts

Step 1: Sign Up for API Key

To get started, sign up on CometAPI and create your API key from the dashboard. After that, store the key securely and use it to authenticate every request you send to the kling-tts model.

Step 2: Send Requests to kling-tts API

Use CometAPI's Kling TTS endpoint at POST /kling/v1/audio/tts.

curl https://api.cometapi.com/kling/v1/audio/tts \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_API_KEY" \
  -d '{
    "text": "Welcome to CometAPI!",
    "voice_id": "genshin_vindi2",
    "voice_language": "en",
    "voice_speed": 1.0
  }'

Step 3: Retrieve and Verify Results

The API returns a task object with the generated audio. Poll the task status endpoint to retrieve the audio output URL when processing is complete.