docs(providers): tighten SenseAudio, Xiaomi, and Inworld ...

Recent Commits to openclaw:main

vincentkoc · 2026-05-06 · via Recent Commits to openclaw:main

Original file line number	Diff line number	Diff line change
`@@ -14,13 +14,18 @@ OpenClaw posts to Inworld's streaming TTS endpoint, concatenates the`
`14`	`14`	`returned base64 audio chunks into a single buffer, and hands the result to`
`15`	`15`	`the standard reply-audio pipeline.`
`16`	`16`
`17`		`-\| Detail \| Value \|`
`18`		`-\| ------------- \| ----------------------------------------------------------- \|`
`19`		`-\| Website \| [inworld.ai](https://inworld.ai) \|`
`20`		`-\| Docs \| [docs.inworld.ai/tts/tts](https://docs.inworld.ai/tts/tts) \|`
`21`		-\| Auth \| `INWORLD_API_KEY` (HTTP Basic, Base64 dashboard credential) \|
`22`		-\| Default voice \| `Sarah` \|
`23`		-\| Default model \| `inworld-tts-1.5-max` \|
	`17`	`+\| Property \| Value \|`
	`18`	`+\| ------------- \| --------------------------------------------------------------- \|`
	`19`	+\| Provider id \| `inworld` \|
	`20`	+\| Plugin \| bundled, `enabledByDefault: true` \|
	`21`	+\| Contract \| `speechProviders` (TTS only) \|
	`22`	+\| Auth env var \| `INWORLD_API_KEY` (HTTP Basic, Base64 dashboard credential) \|
	`23`	+\| Base URL \| `https://api.inworld.ai` \|
	`24`	+\| Default voice \| `Sarah` \|
	`25`	+\| Default model \| `inworld-tts-1.5-max` \|
	`26`	`+\| Output \| MP3 (default), OGG_OPUS (voice notes), PCM 22050 Hz (telephony) \|`
	`27`	`+\| Website \| [inworld.ai](https://inworld.ai) \|`
	`28`	`+\| Docs \| [docs.inworld.ai/tts/tts](https://docs.inworld.ai/tts/tts) \|`
`24`	`29`
`25`	`30`	`## Getting started`
`26`	`31`

Original file line number	Diff line number	Diff line change
`@@ -6,22 +6,20 @@ read_when:`
`6`	`6`	`title: "SenseAudio"`
`7`	`7`	`---`
`8`	`8`
`9`		`-# SenseAudio`
	`9`	+SenseAudio can transcribe inbound audio and voice-note attachments through OpenClaw's shared `tools.media.audio` pipeline. OpenClaw posts multipart audio to the OpenAI-compatible transcription endpoint and injects the returned text as `{{Transcript}}` plus an `[Audio]` block.
`10`	`10`
`11`		`-SenseAudio can transcribe inbound audio/voice-note attachments through`
`12`		-OpenClaw's shared `tools.media.audio` pipeline. OpenClaw posts multipart audio
`13`		`-to the OpenAI-compatible transcription endpoint and injects the returned text`
`14`		-as `{{Transcript}}` plus an `[Audio]` block.
`15`		`-`
`16`		`-\| Detail \| Value \|`
	`11`	`+\| Property \| Value \|`
`17`	`12`	`\| ------------- \| ------------------------------------------------ \|`
`18`		`-\| Website \| [senseaudio.cn](https://senseaudio.cn) \|`
`19`		`-\| Docs \| [senseaudio.cn/docs](https://senseaudio.cn/docs) \|`
`20`		-\| Auth \| `SENSEAUDIO_API_KEY` \|
	`13`	+\| Provider id \| `senseaudio` \|
	`14`	+\| Plugin \| bundled, `enabledByDefault: true` \|
	`15`	+\| Contract \| `mediaUnderstandingProviders` (audio) \|
	`16`	+\| Auth env var \| `SENSEAUDIO_API_KEY` \|
`21`	`17`	\| Default model \| `senseaudio-asr-pro-1.5-260319` \|
`22`	`18`	\| Default URL \| `https://api.senseaudio.cn/v1` \|
	`19`	`+\| Website \| [senseaudio.cn](https://senseaudio.cn) \|`
	`20`	`+\| Docs \| [senseaudio.cn/docs](https://senseaudio.cn/docs) \|`
`23`	`21`
`24`		`-## Getting Started`
	`22`	`+## Getting started`
`25`	`23`
`26`	`24`	`<Steps>`
`27`	`25`	`<Step title="Set your API key">`

Original file line number	Diff line number	Diff line change
`@@ -6,15 +6,20 @@ read_when:`
`6`	`6`	`title: "Xiaomi MiMo"`
`7`	`7`	`---`
`8`	`8`
`9`		`-Xiaomi MiMo is the API platform for MiMo models. OpenClaw uses the Xiaomi`
`10`		`-OpenAI-compatible endpoint with API-key authentication.`
`11`		`-`
`12`		`-\| Property \| Value \|`
`13`		`-\| -------- \| ------------------------------- \|`
`14`		-\| Provider \| `xiaomi` \|
`15`		-\| Auth \| `XIAOMI_API_KEY` \|
`16`		`-\| API \| OpenAI-compatible \|`
`17`		-\| Base URL \| `https://api.xiaomimimo.com/v1` \|
	`9`	+Xiaomi MiMo is the API platform for MiMo models. OpenClaw includes a bundled `xiaomi` plugin that registers both an OpenAI-compatible chat provider and a speech (TTS) provider against the same `XIAOMI_API_KEY`.
	`10`	`+`
	`11`	`+\| Property \| Value \|`
	`12`	`+\| --------------- \| ---------------------------------------- \|`
	`13`	+\| Provider id \| `xiaomi` \|
	`14`	+\| Plugin \| bundled, `enabledByDefault: true` \|
	`15`	+\| Auth env var \| `XIAOMI_API_KEY` \|
	`16`	+\| Onboarding flag \| `--auth-choice xiaomi-api-key` \|
	`17`	+\| Direct CLI flag \| `--xiaomi-api-key <key>` \|
	`18`	+\| Contracts \| chat completions + `speechProviders` \|
	`19`	+\| API \| OpenAI-compatible (`openai-completions`) \|
	`20`	+\| Base URL \| `https://api.xiaomimimo.com/v1` \|
	`21`	+\| Default model \| `xiaomi/mimo-v2-flash` \|
	`22`	+\| TTS default \| `mimo-v2.5-tts`, voice `mimo_default` \|
`18`	`23`
`19`	`24`	`## Getting started`
`20`	`25`

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。

推荐订阅源

Recent Commits to openclaw:main