媒体 API：图片、视频、音乐与音频

媒体 API 统一提供生成、任务查询、模型目录和成本估算。每个模型仍有自己的模式、必填参数和输入限制。

从目录获取公开 model ID、能力、模式和限制。
创建任务后使用轮询或 webhook；结果有保存期限。
系统可能预留估算金额，完成后按实际结果调整，失败时释放预留。

完整示例

原始指南中的可执行示例完整保留如下。只运行适用于你的工具和操作系统的代码块。

bash

curl https://nordrouter.com/media/generate \
  -H "Authorization: Bearer sk-nr-YOUR-KEY" -H "Content-Type: application/json" \
  -d '{ "model": "video/kling-2.6-i2v",
        "input": { "prompt": "slow camera push-in", "image": "https://…/photo.png", "duration": "5", "sound": true } }'

json

{ "id": "b1f2…", "model": "video/kling-2.6-i2v", "status": "processing", "poll": "https://nordrouter.com/media/job/b1f2…" }

bash

curl https://nordrouter.com/media/job/b1f2…

json

{ "id": "b1f2…", "status": "done", "result_url": "https://nordrouter.com/media/file/b1f2…", "cost_usd": 0.55, "error": null }

json

{ "model": "image/flux2-pro", "input": { "prompt": "neon fox in snow", "aspect_ratio": "16:9", "resolution": "2K" } }

json

{ "model": "image/seedream-edit", "input": { "prompt": "remove background, add neon", "image": "https://…/photo.png" } }

json

{ "model": "video/wan-2.7-i2v", "input": {
    "prompt": "slow camera push-in", "image": "https://…/first.png",
    "image2": "https://…/last.png", "duration": 8, "resolution": "1080p" } }

json

{ "model": "music/suno-v5", "input": { "title": "Northern Lights", "style": "epic orchestral", "instrumental": true, "version": "V5_5" } }

json

{ "model": "audio/gemini-3.1-flash-tts", "input": {
    "text": "Hello world", "voice": "Zephyr", "style": "Empathetic",
    "pace": "Natural", "accent": "Neutral" } }

json

{ "model": "video/omnihuman", "input": { "image": "https://…/face.png", "audio_url": "https://…/voice.mp3" } }

bash

curl https://nordrouter.com/media/estimate \
  -H "Authorization: Bearer sk-nr-YOUR-KEY" -H "Content-Type: application/json" \
  -d '{ "model": "video/kling-3.0", "input": { "duration": 10, "mode": "pro", "sound": true } }'

json

{ "model": "video/kling-3.0", "usd": 1.6875 }

官方资料与相关链接

Method	Purpose
`POST /media/generate`	Create a generation task
`GET /media/job/:id`	Task status and result
`POST /media/estimate`	Get a config's price up front
`GET /media/models`	Machine-readable list of models and params
`POST /media/upload`	Upload a source media file
`GET /media/file/:id`	The finished file (link from `result_url`)

`model`	Mode	`input` params	File	Price
`image/nano-banana`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3\|3:2\|2:3\|21:9\|auto, `nsfw_checker`=bool	PNG	$0.025
`image/nano-banana-2`	text→image	`prompt` *, `aspect_ratio`=auto\|1:1\|16:9\|9:16\|3:4\|4:3\|21:9, `resolution`=1K\|2K\|4K, `image`=url, `nsfw_checker`=bool	PNG	$0.050
`image/nano-banana-2-lite`	text→image	`prompt` *, `aspect_ratio`=auto\|1:1\|16:9\|9:16\|3:4\|4:3, `image`=url, `nsfw_checker`=bool	PNG	$0.025
`image/nano-banana-pro`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3\|21:9\|auto, `resolution`=1K\|2K\|4K, `image`=url, `nsfw_checker`=bool	PNG	$0.11
`image/imagen4-fast`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3, `nsfw_checker`=bool	PNG	$0.025
`image/imagen4`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3, `nsfw_checker`=bool	PNG	$0.050
`image/imagen4-ultra`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3, `nsfw_checker`=bool	PNG	$0.075
`image/gpt-image-1.5`	text→image	`prompt` *, `aspect_ratio`=1:1\|2:3\|3:2, `quality`=medium\|high, `nsfw_checker`=bool	PNG	$0.025
`image/gpt-image-1.5-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=3:2\|1:1\|2:3, `quality`=medium\|high, `nsfw_checker`=bool	PNG	$0.025
`image/gpt-image-2`	text→image	`prompt` *, `aspect_ratio`=1:1\|3:2\|2:3\|16:9\|9:16\|4:3\|3:4, `resolution`=1K\|2K\|4K	PNG	$0.006
`image/gpt-image-2-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=auto\|1:1\|3:2\|2:3\|16:9\|9:16, `resolution`=1K\|2K\|4K, `nsfw_checker`=bool	PNG	$0.037
`image/flux2-pro`	text→image	`prompt` *, `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|3:2\|2:3, `resolution`=1K\|2K, `nsfw_checker`=bool	PNG	$0.031
`image/flux2-pro-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|3:2\|2:3\|auto, `resolution`=1K\|2K, `nsfw_checker`=bool	PNG	$0.031
`image/flux2-flex`	text→image	`prompt` *, `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|3:2\|2:3, `resolution`=1K\|2K, `nsfw_checker`=bool	PNG	$0.087
`image/flux2-flex-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|3:2\|2:3\|auto, `resolution`=1K\|2K, `nsfw_checker`=bool	PNG	$0.087
`image/seedream-edit`	image edit	`prompt` , `image`=url , `image_size`=square_hd\|square\|portrait_4_3\|portrait_16_9\|landscape_4_3\|landscape_16_9, `image_resolution`=1K\|2K\|4K, `nsfw_checker`=bool	PNG	$0.037
`image/seedream-4.5-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|2:3\|3:2, `quality`=basic\|high, `nsfw_checker`=bool	PNG	$0.044
`image/seedream-5-lite-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|2:3\|3:2, `quality`=basic\|high, `nsfw_checker`=bool	PNG	$0.037
`image/seedream-5.0-pro-edit`	image edit	`prompt` , `image`=url , `aspect_ratio`=1:1\|4:3\|3:4\|16:9\|9:16\|2:3\|3:2\|21:9, `quality`=basic\|high, `nsfw_checker`=bool	PNG	$0.044
`image/ideogram-v3`	text→image	`prompt` *, `rendering_speed`=TURBO\|BALANCED\|QUALITY, `image_size`=square_hd\|square\|portrait_4_3\|portrait_16_9\|landscape_4_3\|landscape_16_9, `style`=AUTO\|GENERAL\|REALISTIC\|DESIGN, `nsfw_checker`=bool	PNG	$0.044
`image/ideogram-edit`	image edit	`prompt` , `image`=url , `rendering_speed`=TURBO\|BALANCED\|QUALITY, `image_size`=square_hd\|square\|portrait_4_3\|portrait_16_9\|landscape_4_3\|landscape_16_9, `nsfw_checker`=bool	PNG	$0.044
`image/ideogram-character`	image edit	`prompt` , `image`=url , `rendering_speed`=TURBO\|BALANCED\|QUALITY, `style`=AUTO\|REALISTIC\|FICTION, `nsfw_checker`=bool	PNG	$0.11
`image/qwen`	text→image	`prompt` *, `image_size`=square_hd\|square\|portrait_4_3\|portrait_16_9\|landscape_4_3\|landscape_16_9, `nsfw_checker`=bool	PNG	$0.031
`image/qwen-edit`	image edit	`prompt` , `image`=url , `image_size`=square_hd\|square\|portrait_4_3\|portrait_16_9\|landscape_4_3\|landscape_16_9, `nsfw_checker`=bool	PNG	$0.037
`image/qwen-i2i`	image edit	`prompt` , `image`=url , `nsfw_checker`=bool	PNG	$0.031
`image/qwen2-edit`	image edit	`prompt` , `image`=url , `image_size`=16:9\|1:1\|3:4\|4:3\|9:16\|3:2\|2:3, `nsfw_checker`=bool	PNG	$0.037
`image/grok`	text→image	`prompt` *, `aspect_ratio`=1:1\|2:3\|3:2\|16:9\|9:16, `enable_pro`=bool, `nsfw_checker`=bool	PNG	$0.025
`image/grok-edit`	image edit	`prompt` , `image`=url , `nsfw_checker`=bool	PNG	$0.025
`image/z-image`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|3:4\|4:3, `nsfw_checker`=bool	PNG	$0.006
`image/wan-2.7`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|4:3\|3:4\|21:9, `resolution`=1K\|2K\|4K, `image`=url, `nsfw_checker`=bool	PNG	$0.031
`image/wan-2.7-pro`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|4:3\|3:4\|21:9, `resolution`=1K\|2K\|4K, `image`=url, `nsfw_checker`=bool	PNG	$0.075
`image/seedream-5.0-pro`	text→image	`prompt` *	JPG	$0.013
`image/gemini-3.1-flash`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|4:3\|3:4, `resolution`=1K\|2K\|4K	PNG	$0.013
`image/gemini-3-pro`	text→image	`prompt` *, `aspect_ratio`=1:1\|16:9\|9:16\|4:3\|3:4, `resolution`=1K\|2K\|4K	PNG	$0.031

`model`	Mode	`input` params	File	Price
`video/veo-3.1-fast`	text→video	`prompt` *, `aspect_ratio`=16:9\|9:16, `image`=url	MP4	$0.38
`video/veo-3.1-quality`	text→video	`prompt` *, `aspect_ratio`=16:9\|9:16, `image`=url	MP4	$1.56
`video/veo-3.1-lite`	text→video	`prompt` *, `aspect_ratio`=16:9\|9:16, `image`=url	MP4	$0.19
`video/gemini-omni`	text→video	`prompt` *, `duration`=4\|6\|8\|10, `aspect_ratio`=16:9\|9:16, `resolution`=720p\|1080p\|4k, `image`=url, `nsfw_checker`=bool	MP4	$0.66
`video/gemini-omni-flash`	text→video	`prompt` *, `attachments`=upload[]	MP4	$0.13
`video/pixverse-v6`	text→video	`prompt` *, `duration`=1–15s, `quality`=360p\|540p\|720p\|1080p, `generate_audio_switch`=bool, `aspect_ratio`=16:9\|4:3\|1:1\|3:4\|9:16\|2:3\|3:2\|21:9, `generate_multi_clip_switch`=bool, `nsfw_checker`=bool	MP4	$0.045/sec
`video/pixverse-v6-i2v`	image→video	`prompt` , `image`=url , `image2`=url, `duration`=1–15s, `quality`=360p\|540p\|720p\|1080p, `generate_audio_switch`=bool, `generate_multi_clip_switch`=bool, `nsfw_checker`=bool	MP4	$0.045/sec
`video/pixverse-v6-transition`	image→video	`prompt` , `image`=url , `image2`=url *, `duration`=1–15s, `quality`=360p\|540p\|720p\|1080p, `generate_audio_switch`=bool, `nsfw_checker`=bool	MP4	$0.045/sec
`video/pixverse-v6-reference`	image→video	`prompt` , `attachments`=upload[] , `duration`=1–15s, `quality`=360p\|540p\|720p\|1080p, `generate_audio_switch`=bool, `aspect_ratio`=16:9\|4:3\|1:1\|3:4\|9:16\|2:3\|3:2\|21:9, `nsfw_checker`=bool	MP4	$0.051/sec
`video/kling-3.0`	text→video	`prompt` *, `duration`=3–15s, `aspect_ratio`=16:9\|9:16\|1:1, `mode`=std\|pro\|4K, `sound`=bool, `image`=url, `image2`=url, `nsfw_checker`=bool	MP4	$0.11/sec
`video/kling-t2v`	text→video	`prompt` *, `duration`=3–15s, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.11/sec
`video/kling-turbo-i2v`	image→video	`prompt` , `image`=url , `duration`=3–15s, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.11/sec
`video/kling-2.6-t2v`	text→video	`prompt` *, `duration`=5\|10, `aspect_ratio`=16:9\|9:16\|1:1, `sound`=bool, `nsfw_checker`=bool	MP4	$0.34
`video/kling-2.6-i2v`	image→video	`prompt` , `image`=url , `duration`=5\|10, `sound`=bool, `nsfw_checker`=bool	MP4	$0.34
`video/kling-2.5-t2v`	text→video	`prompt` *, `duration`=5\|10, `aspect_ratio`=16:9\|9:16\|1:1, `nsfw_checker`=bool	MP4	$0.26
`video/kling-2.5-i2v`	image→video	`prompt` , `image`=url , `image2`=url, `duration`=5\|10, `nsfw_checker`=bool	MP4	$0.26
`video/kling-i2v`	image→video	`prompt` , `image`=url , `image2`=url, `duration`=5\|10, `nsfw_checker`=bool	MP4	$0.31
`video/kling-2.1-standard`	image→video	`prompt` , `image`=url , `duration`=5\|10, `nsfw_checker`=bool	MP4	$0.16
`video/kling-2.1-master-t2v`	text→video	`prompt` *, `duration`=5\|10, `aspect_ratio`=16:9\|9:16\|1:1, `nsfw_checker`=bool	MP4	$1.00
`video/kling-2.1-master-i2v`	image→video	`prompt` , `image`=url , `duration`=5\|10, `nsfw_checker`=bool	MP4	$1.00
`video/kling-motion`	video→video	`image`=url , `video_url` , `prompt`, `mode`=std\|pro	MP4	$1.25
`video/kling-avatar`	avatar (photo+audio)	`image`=url , `audio_url` , `prompt` *	MP4	$0.75
`video/kling-avatar-pro`	avatar (photo+audio)	`image`=url , `audio_url` , `prompt` *	MP4	$1.50
`video/wan-2.7-t2v`	text→video	`prompt` *, `duration`=2–15s, `ratio`=16:9\|9:16\|1:1\|4:3\|3:4, `resolution`=720p\|1080p, `audio_url`, `nsfw_checker`=bool	MP4	$0.15/sec
`video/wan-2.7-i2v`	image→video	`prompt` , `image`=url , `image2`=url, `duration`=2–15s, `resolution`=720p\|1080p, `audio_url`, `nsfw_checker`=bool	MP4	$0.15/sec
`video/wan-2.7-r2v`	image→video	`prompt` , `image`=url , `duration`=2–10s, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.15/sec
`video/wan-2.7-edit`	video→video	`prompt` , `video_url` , `resolution`=720p\|1080p, `audio_setting`=auto\|origin	MP4	$1.50
`video/wan-t2v`	text→video	`prompt` *, `duration`=5\|10\|15, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.44
`video/wan-i2v`	image→video	`prompt` , `image`=url , `duration`=5\|10\|15, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.44
`video/wan-v2v`	video→video	`prompt` , `video_url` , `duration`=5\|10, `resolution`=720p\|1080p	MP4	$0.44
`video/wan-2.5-t2v`	text→video	`prompt` *, `duration`=5\|10, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.38
`video/wan-2.5-i2v`	image→video	`prompt` , `image`=url , `duration`=5\|10, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.38
`video/wan-2.2-t2v`	text→video	`prompt` *, `aspect_ratio`=16:9\|9:16, `resolution`=480p\|720p, `nsfw_checker`=bool	MP4	$0.50
`video/wan-2.2-i2v`	image→video	`prompt` , `image`=url , `resolution`=480p\|720p, `nsfw_checker`=bool	MP4	$0.50
`video/wan-s2v`	avatar (photo+audio)	`prompt` , `image`=url , `audio_url` *, `resolution`=480p\|580p\|720p	MP4	$0.38
`video/wan-animate-move`	video→video	`image`=url , `video_url` , `resolution`=480p\|580p\|720p	MP4	$0.38
`video/wan-animate-replace`	video→video	`image`=url , `video_url` , `resolution`=480p\|580p\|720p	MP4	$0.38
`video/seedance-2`	text→video	`prompt` *, `duration`=4–15s, `aspect_ratio`=16:9\|9:16\|1:1\|4:3\|21:9, `resolution`=480p\|720p\|1080p\|4k, `generate_audio`=bool, `image`=url, `image2`=url, `nsfw_checker`=bool	MP4	$0.26/sec
`video/seedance-2-fast`	text→video	`prompt` *, `duration`=4–15s, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=480p\|720p, `generate_audio`=bool, `image`=url, `image2`=url, `nsfw_checker`=bool	MP4	$0.21/sec
`video/seedance-2-mini`	text→video	`prompt` *, `duration`=4–15s, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=480p\|720p, `generate_audio`=bool, `image`=url, `image2`=url, `nsfw_checker`=bool	MP4	$0.13/sec
`video/seedance-1.5-pro`	text→video	`prompt` *, `duration`=4–12s, `aspect_ratio`=16:9\|9:16\|1:1\|4:3, `resolution`=480p\|720p\|1080p, `generate_audio`=bool, `image`=url, `nsfw_checker`=bool	MP4	$0.025/sec
`video/hailuo-02-t2v`	text→video	`prompt` *, `duration`=6\|10, `nsfw_checker`=bool	MP4	$0.19
`video/hailuo-02-t2v-pro`	text→video	`prompt` *, `nsfw_checker`=bool	MP4	$0.36
`video/hailuo-02-i2v`	image→video	`prompt` , `image`=url , `image2`=url, `duration`=6\|10, `resolution`=768P\|512P, `nsfw_checker`=bool	MP4	$0.19
`video/hailuo-02-i2v-pro`	image→video	`prompt` , `image`=url , `image2`=url, `nsfw_checker`=bool	MP4	$0.36
`video/hailuo-2.3-i2v`	image→video	`prompt` , `image`=url , `duration`=6\|10, `resolution`=768P\|1080P, `nsfw_checker`=bool	MP4	$0.19
`video/hailuo-2.3-i2v-pro`	image→video	`prompt` , `image`=url , `duration`=6\|10, `resolution`=768P\|1080P, `nsfw_checker`=bool	MP4	$0.28
`video/happyhorse-1.1-t2v`	text→video	`prompt` *, `duration`=3–15s, `aspect_ratio`=16:9\|9:16\|1:1\|4:3\|3:4, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.18/sec
`video/happyhorse-1.1-i2v`	image→video	`prompt`, `image`=url *, `duration`=3–15s, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.18/sec
`video/happyhorse-1.1-r2v`	image→video	`prompt` , `image`=url , `duration`=3–15s, `aspect_ratio`=16:9\|9:16\|1:1, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.18/sec
`video/happyhorse-t2v`	text→video	`prompt` *, `duration`=3–15s, `aspect_ratio`=16:9\|9:16\|1:1\|4:3\|3:4, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.30/sec
`video/happyhorse-i2v`	image→video	`prompt`, `image`=url *, `duration`=3–15s, `resolution`=720p\|1080p, `nsfw_checker`=bool	MP4	$0.30/sec
`video/happyhorse-edit`	video→video	`prompt` , `video_url` , `resolution`=720p\|1080p, `audio_setting`=auto\|origin	MP4	$1.50
`video/grok-t2v`	text→video	`prompt` *, `duration`=6–30s, `aspect_ratio`=16:9\|9:16\|1:1\|3:2\|2:3, `resolution`=480p\|720p, `mode`=normal\|fun\|spicy, `nsfw_checker`=bool	MP4	$0.019/sec
`video/grok-i2v`	image→video	`prompt` , `image`=url , `duration`=6–30s, `resolution`=480p\|720p, `mode`=normal\|fun\|spicy, `nsfw_checker`=bool	MP4	$0.019/sec
`video/grok-1.5`	text→video	`prompt` *, `duration`=1–15s, `aspect_ratio`=auto\|16:9\|9:16\|1:1, `resolution`=480p\|720p, `image`=url, `nsfw_checker`=bool	MP4	$0.019/sec
`video/omnihuman`	avatar (photo+audio)	`image`=url , `audio_url` , `prompt`, `output_resolution`=720\|1080	MP4	$1.69
`video/infinitalk`	avatar (photo+audio)	`prompt` , `image`=url , `audio_url` *, `resolution`=480p\|720p	MP4	$0.19
`video/lipsync`	video→video	`video_url` , `audio_url` , `mode`=lite\|basic	MP4	$0.50
`video/topaz-upscale`	upscale	`video_url` *, `upscale_factor`=2\|4	MP4	$0.50

`model`	Mode	`input` params	File	Price
`music/suno-v5`	music	`title` , `style` , `version`=V5_5\|V5\|V4_5ALL\|V4_5PLUS\|V4_5\|V4, `instrumental`=bool, `prompt`	MP3	$0.075
`music/suno-cover`	music	`prompt` , `attachments`=upload[] , `version`=V5_5\|V5\|V4_5ALL\|V4_5PLUS\|V4_5\|V4, `instrumental`=bool	MP3	$0.075
`music/suno-extend-upload`	music	`prompt` , `attachments`=upload[] , `version`=V5_5\|V5\|V4_5ALL\|V4_5PLUS\|V4_5\|V4, `continueAt`=1–120, `instrumental`=bool	MP3	$0.075
`music/suno-add-vocals`	music	`prompt` , `attachments`=upload[] , `version`=V4_5PLUS, `style`, `title`, `negativeTags`, `vocalGender`=f\|m	MP3	$0.075
`music/suno-add-instrumental`	music	`prompt` , `attachments`=upload[] , `version`=V4_5PLUS, `title`, `negativeTags`	MP3	$0.075
`music/suno-mashup`	music	`prompt` , `attachments`=upload[] , `version`=V5_5\|V5\|V4_5ALL\|V4_5PLUS\|V4_5\|V4, `instrumental`=bool	MP3	$0.075
`music/suno-sounds`	music	`prompt` *, `version`=V5_5\|V5\|V4_5ALL\|V4_5PLUS\|V4_5\|V4, `soundLoop`=bool, `soundTempo`=auto\|60\|80\|100\|120\|140\|160, `soundKey`=auto\|C\|Dm\|Em\|F\|G\|Am\|D#m	MP3	$0.016

`model`	Mode	`input` params	File	Price
`audio/gemini-3.1-flash-tts`	text-to-speech	`text` *, `voice`=Achernar\|Achird\|Algenib\|Algieba\|Alnilam\|Aoede\|Autonoe\|Callirrhoe\|Charon\|Despina\|Enceladus\|Erinome\|Fenrir\|Gacrux\|Iapetus\|Kore\|Laomedeia\|Leda\|Orus\|Puck\|Pulcherrima\|Rasalgethi\|Sadachbia\|Sadaltager\|Schedar\|Sulafat\|Umbriel\|Vindemiatrix\|Zephyr\|Zubenelgenubi, `style`=Vocal Smile\|Newscaster\|Whisper\|Empathetic\|Promo/Hype\|Deadpan, `pace`=Natural\|Rapid Fire\|The Drift\|Staccato, `accent`=Neutral\|American (Gen)\|American (Valley)\|American (South)\|British (RP)\|British (Brixton)\|Transatlantic\|Australian, `audio_profile`, `scene`, `temperature`=0–2	WAV	$0.006
`audio/gemini-2.5-pro-tts`	text-to-speech	`text` *, `voice`=Achernar\|Achird\|Algenib\|Algieba\|Alnilam\|Aoede\|Autonoe\|Callirrhoe\|Charon\|Despina\|Enceladus\|Erinome\|Fenrir\|Gacrux\|Iapetus\|Kore\|Laomedeia\|Leda\|Orus\|Puck\|Pulcherrima\|Rasalgethi\|Sadachbia\|Sadaltager\|Schedar\|Sulafat\|Umbriel\|Vindemiatrix\|Zephyr\|Zubenelgenubi, `style`=Vocal Smile\|Newscaster\|Whisper\|Empathetic\|Promo/Hype\|Deadpan, `pace`=Natural\|Rapid Fire\|The Drift\|Staccato, `accent`=Neutral\|American (Gen)\|American (Valley)\|American (South)\|British (RP)\|British (Brixton)\|Transatlantic\|Australian, `audio_profile`, `scene`, `temperature`=0–2	WAV	$0.006
`audio/elevenlabs-tts`	text-to-speech	`text` *, `voice`=James · Husky, Engaging and Bold\|Addison · Australian, Audiobook & Podcast\|Adeline · Feminine and Conversational\|Allison · Calm, Soothing and Meditative\|Ana Rita · Smooth, Expressive and Bright\|Anika · Animated, Friendly and Engaging\|Arabella · Mysterious and Emotive\|Aria · Sultry Villain\|Bella · Professional, Bright, Warm\|Benjamin · Deep, Warm, Calming\|Bradford · Expressive and Articulate\|Brian · Deep, Resonant and Comforting\|Britney · Calm and Calculative Villain\|Brittney · Fun, Youthful & Informative\|Brock · Commanding and Loud Sergeant\|Burt · Deep, Smooth and Clear\|Callum · Husky Trickster\|Cassidy · Crisp, Direct and Clear\|Ed · Late Night Announcer\|Edward · Loud, Confident and Cocky\|Emma · Adorable and Upbeat\|Eve · Authentic, Energetic and Happy\|Felix · Warm, Positive & Contemporary\|Finn · Youthful, Eager and Energetic\|Hank · Deep and Engaging Narrator\|Hope · Poetic, Romantic and Captivating\|Hope · Bubbly, Gossipy and Girly\|Horatius · Energetic Character Voice\|Jamahal · Young, Vibrant, and Natural\|Jean · Alluring and Playful Femme Fatale\|Jeff · Classy, Resonating and Strong\|Jessica · Eloquent Villain\|Jessica · Chatty and Friendly\|John Doe · Deep\|John Morgan · Gritty, Rugged Cowboy\|Johnny Dynamite · Vintage Radio DJ\|Johnny Kid · Serious and Calm Narrator\|Kuon · Cheerful, Clear and Steady\|Laura · Enthusiast, Quirky Attitude\|Leon · Soothing and Grounded\|Liam · Energetic, Social Media Creator\|Lucy · Fresh & Casual\|Lutz · Chuckling, Giggly and Cheerful\|Mark · Casual, Relaxed and Light\|Mark · Natural Conversations\|Marshal · Friendly, Funny Professor\|Monika · Deep and Natural\|Nathan · Virtual Radio Host\|Nathaniel · Engaging, British and Calm\|Phil · Explosive, Passionate Announcer\|Rachel · Pro British Radio Presenter\|Rex Thunder · Deep N Tough\|Sam · Support Agent\|Spuds · Wise and Approachable\|Sven · Emotional and Nice\|Taksh · Calm, Serious and Smooth\|Theodore · Serene and Grounded\|Tiffany · Natural and Welcoming\|Tom · Conversations & Books\|Viking Bjorn · Epic Medieval Raider\|Viraj · Smooth and Gentle\|Viraj · Rich and Soft\|Wyatt · Wise Rustic Cowboy\|Xavier · Dominating, Metallic Announcer, `voice_id`, `speed`=0.8\|1.0\|1.2	MP3	$0.037
`audio/elevenlabs-multilingual`	text-to-speech	`text` *, `voice`=James · Husky, Engaging and Bold\|Addison · Australian, Audiobook & Podcast\|Adeline · Feminine and Conversational\|Allison · Calm, Soothing and Meditative\|Ana Rita · Smooth, Expressive and Bright\|Anika · Animated, Friendly and Engaging\|Arabella · Mysterious and Emotive\|Aria · Sultry Villain\|Bella · Professional, Bright, Warm\|Benjamin · Deep, Warm, Calming\|Bradford · Expressive and Articulate\|Brian · Deep, Resonant and Comforting\|Britney · Calm and Calculative Villain\|Brittney · Fun, Youthful & Informative\|Brock · Commanding and Loud Sergeant\|Burt · Deep, Smooth and Clear\|Callum · Husky Trickster\|Cassidy · Crisp, Direct and Clear\|Ed · Late Night Announcer\|Edward · Loud, Confident and Cocky\|Emma · Adorable and Upbeat\|Eve · Authentic, Energetic and Happy\|Felix · Warm, Positive & Contemporary\|Finn · Youthful, Eager and Energetic\|Hank · Deep and Engaging Narrator\|Hope · Poetic, Romantic and Captivating\|Hope · Bubbly, Gossipy and Girly\|Horatius · Energetic Character Voice\|Jamahal · Young, Vibrant, and Natural\|Jean · Alluring and Playful Femme Fatale\|Jeff · Classy, Resonating and Strong\|Jessica · Eloquent Villain\|Jessica · Chatty and Friendly\|John Doe · Deep\|John Morgan · Gritty, Rugged Cowboy\|Johnny Dynamite · Vintage Radio DJ\|Johnny Kid · Serious and Calm Narrator\|Kuon · Cheerful, Clear and Steady\|Laura · Enthusiast, Quirky Attitude\|Leon · Soothing and Grounded\|Liam · Energetic, Social Media Creator\|Lucy · Fresh & Casual\|Lutz · Chuckling, Giggly and Cheerful\|Mark · Casual, Relaxed and Light\|Mark · Natural Conversations\|Marshal · Friendly, Funny Professor\|Monika · Deep and Natural\|Nathan · Virtual Radio Host\|Nathaniel · Engaging, British and Calm\|Phil · Explosive, Passionate Announcer\|Rachel · Pro British Radio Presenter\|Rex Thunder · Deep N Tough\|Sam · Support Agent\|Spuds · Wise and Approachable\|Sven · Emotional and Nice\|Taksh · Calm, Serious and Smooth\|Theodore · Serene and Grounded\|Tiffany · Natural and Welcoming\|Tom · Conversations & Books\|Viking Bjorn · Epic Medieval Raider\|Viraj · Smooth and Gentle\|Viraj · Rich and Soft\|Wyatt · Wise Rustic Cowboy\|Xavier · Dominating, Metallic Announcer, `voice_id`, `speed`=0.8\|1.0\|1.2	MP3	$0.075
`audio/elevenlabs-isolation`	audio	`audio_url` *	MP3	$0.063

`model`	Mode	`input` params	File	Price
`image/topaz-upscale`	upscale	`image`=url *, `upscale_factor`=2\|4\|8	PNG	$0.063
`image/recraft-remove-bg`	edit	`image`=url *	PNG	$0.006
`image/recraft-upscale`	upscale	`image`=url *	PNG	$0.006

Status	Meaning
`processing`	In progress — keep polling
`done`	Ready — file in `result_url`, charge in `cost_usd`
`failed`	Error — reason in `error`, money refunded

先用最小文本请求验证连接，再添加流式输出、工具调用、图片等高级功能。不要把 API key 放入公开代码或浏览器前端。

故障排除

媒体 API：图片、视频、音乐与音频 ​

完整示例 ​

官方资料与相关链接 ​

媒体 API：图片、视频、音乐与音频

完整示例

官方资料与相关链接