Voice Input

Speak an idea and turn it into text.

What you can do

Voice input is useful for quickly capturing an idea, revision, or longer request. Flova transcribes the recording into text. You can still edit the text, add references, and decide whether to send it.

How to use it

1. Select the microphone beside the chat input on the right side of the project.
2. If the browser requests microphone access, allow it.
3. Start speaking and watch the recognized text appear in the input.
4. Select the microphone again when you finish, then wait for the final words to be transcribed.
5. Review the text, add any missing media names, shot requirements, or limits, and select Send.

Voice input does not send a message automatically. If the Agent needs specific content, refer to project content before sending.

Tips

• Correct names, media titles, and specialist terms before sending if they were transcribed incorrectly.
• Add explicit references after dictating instead of saying only “use that image”.

Usage limitations

• Voice input requires browser support and microphone permission for the current site.
• Editing the input manually pauses the current voice session.
• A recording ends after a long silence or when it reaches the single-session time limit. Select the microphone again to continue.
• If microphone permission is blocked, enable it in the browser settings before retrying.

Related features

• Generate Media with Agent: give your spoken request to the Agent to carry out.
• Refer to project content: identify the project material for a dictated task.
• Upload media: add a new local file.