> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Kling 2.6 > Kling 2.6 text-to-video and image-to-video, with optional native audio and designated voices. **Pricing** — per second of generated video, in tokens (USD at $0.02/token). Same as the official rate: | configuration | 720p | 1080p | |---|---|---| | No native audio | 2.1 tokens/s ($0.042) | 3.5 tokens/s ($0.07) | | Native audio | not available | 7 tokens/s ($0.14) | | Native audio + voice | not available | 8.4 tokens/s ($0.168) | ⚠️ **A designated voice is a separate price tier**, not a free extra — it is 20% above plain native audio. ⚠️ **Three upstream constraints interact, and this endpoint rejects impossible combinations up front (before any tokens are deducted):** 1. `voice_ids` requires `generate_audio: true` — a designated voice cannot be silent. 2. `generate_audio: true` requires `resolution: 1080p` — Kling publishes no 720p audio tier. 3. A first **and** last frame requires `resolution: 720p`. Rules 2 and 3 are mutually exclusive: **on Kling 2.6 you cannot combine a first+last frame pair with native audio or voices.** Drop `image_end_url`, or drop `generate_audio`. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. ## OpenAPI ````yaml api-reference/video-generations/openapi-kling-2-6.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Kling 2.6 description: Video generation with Kling 2.6. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: Kling 2.6 description: >- Kling 2.6 text-to-video and image-to-video, with optional native audio and designated voices. **Pricing** — per second of generated video, in tokens (USD at $0.02/token). Same as the official rate: | configuration | 720p | 1080p | |---|---|---| | No native audio | 2.1 tokens/s ($0.042) | 3.5 tokens/s ($0.07) | | Native audio | not available | 7 tokens/s ($0.14) | | Native audio + voice | not available | 8.4 tokens/s ($0.168) | ⚠️ **A designated voice is a separate price tier**, not a free extra — it is 20% above plain native audio. ⚠️ **Three upstream constraints interact, and this endpoint rejects impossible combinations up front (before any tokens are deducted):** 1. `voice_ids` requires `generate_audio: true` — a designated voice cannot be silent. 2. `generate_audio: true` requires `resolution: 1080p` — Kling publishes no 720p audio tier. 3. A first **and** last frame requires `resolution: 720p`. Rules 2 and 3 are mutually exclusive: **on Kling 2.6 you cannot combine a first+last frame pair with native audio or voices.** Drop `image_end_url`, or drop `generate_audio`. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - kling-2-6 description: Model name. Must be `kling-2-6`. prompt: type: string maxLength: 2500 description: >- Text prompt. Max 2500 characters. Use `@1` / `@2` to make a designated voice speak. image_url: type: string format: uri description: Optional. First-frame image URL. Omit for text-to-video. image_end_url: type: string format: uri description: >- Optional. Last-frame image URL. Requires `image_url`, and forces `resolution: 720p`. voice_ids: type: array items: type: string maxItems: 2 description: >- Optional. Up to 2 voice ids from Kling's Voice Management API (or a system preset). Order is the `@1` / `@2` numbering. Requires `image_url` (text-to-video has no materials) and `generate_audio: true`. `voice_id` is accepted for a single value. duration: type: integer enum: - 5 - 10 default: 5 description: Video duration in seconds. Only 5 or 10. resolution: type: string enum: - 720p - 1080p default: 720p description: >- Output resolution. No 4K tier. `quality` is accepted as a compatible alias. ratio: type: string enum: - '16:9' - '9:16' - '1:1' default: '16:9' description: >- Output aspect ratio. Text-to-video only — with a first frame the image decides. `aspect_ratio` is accepted as a compatible alias. generate_audio: type: boolean default: false description: >- Generate a native audio track matching the visuals. Requires `resolution: 1080p`, and costs more per second. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - prompt example: model: kling-2-6 prompt: A girl on a train looking out of the window, @1 whispers softly image_url: https://example.com/first-frame.png resolution: 1080p generate_audio: true voice_ids: - '891495440020668439' duration: 5 responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string required: - img_uuid required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false ````