7 个工具 · 7 个可使用平台 key · 0 个仅自有 key
Google AI (Gemini API) API：7 个工具，按次付费
通过 Toolswitch 使用 Google AI (Gemini API) 工具。
常见任务：image-gen.gemini-3-pro-image.generate, voice-gen.gemini-3-8-flash-tts.generate, music-gen.lyria-3-clip.generate。
能做什么
Speak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash-Lite TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
Generate or edit one 1K image with Gemini 3.1 Flash Lite Image on Google's own API, the cheapest Gemini image model; the image returns inline as base64.
Compose a 30-second music clip from a text prompt with Lyria 3 Clip on Google's own API; the MP3 returns inline as base64.
在 Agent 里使用
通过 MCP 将这些工具提供给 Agent，或使用 HTTP 将调用接入你的工作流。
- MCP: 通过 MCP 连接 Agent，以发现和使用工具。
- HTTP: 通过 HTTP API 在应用中调用工具。
为什么通过 Toolswitch 调用？
无需供应商账号
使用平台 key 的工具无需单独注册供应商账号。
按次付费
按实际使用量付费，无需供应商订阅。
价格透明
调用前即可查看工具价格与计费单位。
全部 7 个工具
Image generation · 3 个工具
Generate or edit one 1K image with Gemini 3.1 Flash Lite Image on Google's own API, the cheapest Gemini image model; the image returns inline as base64.
google-ai.image-gen.gemini-3-1-flash-lite-imageGenerate or edit one image with Gemini 3.1 Flash Image at 512px, 1K, 2K or 4K on Google's own API, from a prompt and optional reference images; the image returns inline as base64.
google-ai.image-gen.gemini-3-1-flash-imageGenerate or edit one image with Gemini 3 Pro Image at 1K, 2K or 4K on Google's own API, from a prompt and optional reference image URLs; the image returns inline as base64.
google-ai.image-gen.gemini-3-pro-image
Music generation · 2 个工具
Compose a 30-second music clip from a text prompt with Lyria 3 Clip on Google's own API; the MP3 returns inline as base64.
google-ai.music-gen.lyria-3-clipCompose a full song (about three minutes) from a text prompt with Lyria 3.5 on Google's own API; the MP3 returns inline as base64 with its lyrics or section markers.
google-ai.music-gen.lyria-3-5
Voice generation · 2 个工具
Speak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash-Lite TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
google-ai.voice-gen.gemini-3-8-flash-lite-ttsSpeak a text in one of 30 prebuilt voices, or a two-speaker dialogue, with Gemini 3.8 Flash TTS on Google's own API; the audio returns inline as base64 WAV (24 kHz mono).
google-ai.voice-gen.gemini-3-8-flash-tts
限制与计费
Synchronous: one generateContent call takes about 25-70 seconds and answers with the image inline as base64 (`candidates[0].content.parts[].inlineData.data`), not a URL. A 2K answer is about 9 MB and a 4K one about 23 MB, most of it a `thoughtSignature` that only multi-turn editing needs; add `fields=candidates(content(parts(text,inlineData)),finishReason),usageMetadata,modelVersion,responseId,promptFeedback` to receive about 4 MB (2K) instead. Rate limits and a spend cap per 10 minutes follow the Google Cloud billing account's tier; 429 RESOURCE_EXHAUSTED is that limit, 503 UNAVAILABLE is Google-side demand and is worth a later retry.
官方定价 ↗