Canonical: https://botbento.com/usecases/multimodal-messaging-with-voice-and-image-comprehension/
Format: Markdown representation of the public HTML page.

[Home](/) / [Use cases](/usecases/) / [Personal](/usecases/?category=personal)

Personal · Intermediate

# Multimodal messaging with voice and image comprehension

Process incoming speech notes, analyze photos, and craft conversational replies

[Use with BotBento ](https://app.botbento.com/?ref=usecases&utm_source=botbento.com&utm_medium=usecases&utm_campaign=multimodal-messaging-with-voice-and-image-comprehension)Copy promptShare[Markdown](/text/usecases/multimodal-messaging-with-voice-and-image-comprehension/index.md)

Opens BotBento. Paste the prompt into a bot; nothing is preconfigured.

- When you askReceive voice note or photo
- ThenTranscribe audio and inspect media
- ResultAwait approval to send reply

Ingest inbound chat messages containing text, spoken voice memos, or photos. The bot transcribes incoming audio, analyzes uploaded visual media, queries long-term context from a database, and generates contextual responses or status updates. Outgoing voice clips and messages are reviewed before being transmitted to the recipient.

## Prompt to start with

BotBentoRecommended

```
When an incoming message arrives, check whether it contains text, an audio recording, or an image. Transcribe voice inputs to text and describe image content before generating a response. Consult previous conversation history stored in the database for continuity. Draft your proposed reply—including any generated voice audio or contextual images—and show the complete draft to the user for approval before sending any message.
```

Copy

## Tools it uses

ChatDatabase

## Works with

BotBento

## Tags

- messaging
- voice
- vision
- chat
- multimodal

## Source

[ava-whatsapp-agent-course: Meet Ava, the WhatsApp Agent](https://github.com/neural-maze/ava-whatsapp-agent-course)
GitHub · checked 2026-10-15

Summarized in our own words. Any results described there are the authors’ own, not measured by BotBento.

By BotBento Editorial · Added 2026-10-15 · Updated 2026-10-15 · [Suggest a correction](/contact/)

## Related use cases

-

Personalintermediate

## [Desktop voice query and discussion logging](/usecases/desktop-voice-query-and-discussion-logging/)

Turn spoken discussions and desktop inquiries into structured daily logs and clear answers

BrowserChatNotes
-

Personalintermediate

## [Hands-free voice assistant for workshop tasks](/usecases/hands-free-voice-assistant-for-workshop-tasks/)

Look up specs, calculate measurements, and log project notes purely by voice while your hands are busy

ChatNotesDocs
-

Personalintermediate

## [Interactive mystery suspect interrogation](/usecases/interactive-mystery-suspect-interrogation/)

Interview simulated suspects in character and evaluate formal case accusations

ChatNotesDatabase