Media and attachments
Photo albums, audio, video, and stickers
Photo albums, audio, video, and stickers
Photo albums
Send multiple image attachments in onemessage tool call. OpenClaw groups consecutive photos into Telegram albums of up to 10 images, in their original order. Automatic replies with multiple photos use the same grouping. A single photo, including a final remainder of one, is sent separately.Audio messages
Telegram distinguishes voice notes from audio files. Default: audio-file behavior; tag[[audio_as_voice]] in the agent reply to force a voice-note send. Inbound voice-note transcripts are framed as machine-generated, untrusted text in agent context, but mention detection still uses the raw transcript so mention-gated voice messages keep working.Video messages
Telegram distinguishes video files from video notes. Video notes do not support captions; provided message text sends separately.Locations and venues
Use the existingsend action with one standalone location object. Coordinates send a native pin; adding both name and address sends a native venue card. Location sends cannot be combined with message text or media.Stickers
Inbound: static WEBP is downloaded and processed (placeholder<media:sticker>); animated TGS and video WEBM are skipped.Sticker context fields: Sticker.emoji, Sticker.setName, Sticker.fileId, Sticker.fileUniqueId, Sticker.cachedDescription. Descriptions are cached in OpenClaw SQLite plugin state to reduce repeated vision calls.Sticker descriptions use the configured agents.defaults.imageModel before shared automatic image-model selection, including the provider’s MiniMax image routing. The sticker description uses one selected model and does not try the configured fallback list if that model fails. A failed description is not cached; general media analysis can still run separately with its normal fallback handling.Enable sticker actions: