@@ -18,31 +18,31 @@ OpenClaw generates images, videos, and music, understands inbound media (images,
1818| Image generation | `image_generate` | ComfyUI, fal, Google, MiniMax, OpenAI, Vydra, xAI | Creates or edits images from text prompts or references |
1919| Video generation | `video_generate` | Alibaba, BytePlus, ComfyUI, fal, Google, MiniMax, OpenAI, Qwen, Runway, Together, Vydra, xAI | Creates videos from text, images, or existing videos |
2020| Music generation | `music_generate` | ComfyUI, Google, MiniMax | Creates music or audio tracks from text prompts |
21-| Text-to-speech (TTS) | `tts` | ElevenLabs, Microsoft, MiniMax, OpenAI, xAI | Converts outbound replies to spoken audio |
21+| Text-to-speech (TTS) | `tts` | ElevenLabs, Google, Microsoft, MiniMax, OpenAI, xAI | Converts outbound replies to spoken audio |
2222| Media understanding | (automatic) | Any vision/audio-capable model provider, plus CLI fallbacks | Summarizes inbound images, audio, and video |
23232424## Provider capability matrix
25252626This table shows which providers support which media capabilities across the platform.
272728-| Provider | Image | Video | Music | TTS | STT / Transcription | Media Understanding |
29-| ---------- | ----- | ----- | ----- | --- | ------------------- | ------------------- |
30-| Alibaba | | Yes | | | | |
31-| BytePlus | | Yes | | | | |
32-| ComfyUI | Yes | Yes | Yes | | | |
33-| Deepgram | | | | | Yes | |
34-| ElevenLabs | | | | Yes | Yes | |
35-| fal | Yes | Yes | | | | |
36-| Google | Yes | Yes | Yes | | | Yes |
37-| Microsoft | | | | Yes | | |
38-| MiniMax | Yes | Yes | Yes | Yes | | |
39-| Mistral | | | | | Yes | |
40-| OpenAI | Yes | Yes | | Yes | Yes | Yes |
41-| Qwen | | Yes | | | | |
42-| Runway | | Yes | | | | |
43-| Together | | Yes | | | | |
44-| Vydra | Yes | Yes | | | | |
45-| xAI | Yes | Yes | | Yes | Yes | Yes |
28+| Provider | Image | Video | Music | TTS | STT / Transcription | Realtime Voice | Media Understanding |
29+| ---------- | ----- | ----- | ----- | --- | ------------------- | -------------- | ------------------- |
30+| Alibaba | | Yes | | | | | |
31+| BytePlus | | Yes | | | | | |
32+| ComfyUI | Yes | Yes | Yes | | | | |
33+| Deepgram | | | | | Yes | | |
34+| ElevenLabs | | | | Yes | Yes | | |
35+| fal | Yes | Yes | | | | | |
36+| Google | Yes | Yes | Yes | Yes | | Yes | Yes |
37+| Microsoft | | | | Yes | | | |
38+| MiniMax | Yes | Yes | Yes | Yes | | | |
39+| Mistral | | | | | Yes | | |
40+| OpenAI | Yes | Yes | | Yes | Yes | Yes | Yes |
41+| Qwen | | Yes | | | | | |
42+| Runway | | Yes | | | | | |
43+| Together | | Yes | | | | | |
44+| Vydra | Yes | Yes | | | | | |
45+| xAI | Yes | Yes | | Yes | Yes | | Yes |
46464747<Note>
4848Media understanding uses any vision-capable or audio-capable model registered in your provider config. The table above highlights providers with dedicated media-understanding support; most LLM providers with multimodal models (Anthropic, Google, OpenAI, etc.) can also understand inbound media when configured as the active reply model.
@@ -58,12 +58,14 @@ ElevenLabs, Mistral, OpenAI, and xAI also register Voice Call streaming STT
5858providers, so live phone audio can be forwarded to the selected vendor
5959without waiting for a completed recording.
606061-OpenAI maps to OpenClaw's image, video, batch TTS, batch STT, Voice Call
62-streaming STT, realtime voice, and memory embedding surfaces. xAI currently
63-maps to OpenClaw's image, video, search, code-execution, batch TTS, batch STT,
64-and Voice Call streaming STT surfaces. xAI Realtime voice is an upstream
65-capability, but it is not registered in OpenClaw until the shared realtime
66-voice contract can represent it.
61+Google maps to OpenClaw's image, video, music, batch TTS, backend realtime
62+voice, and media-understanding surfaces. OpenAI maps to OpenClaw's image,
63+video, batch TTS, batch STT, Voice Call streaming STT, backend realtime voice,
64+and memory embedding surfaces. xAI currently maps to OpenClaw's image, video,
65+search, code-execution, batch TTS, batch STT, and Voice Call streaming STT
66+surfaces. xAI Realtime voice is an upstream capability, but it is not
67+registered in OpenClaw until the shared realtime voice contract can represent
68+it.
67696870## Quick links
6971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。