Use the Speak AI MCP server tool get_signed_upload_url to get a pre-signed S3 URL
for direct file upload to Speak AI storage.
What does it do?
Get a pre-signed S3 URL for direct file upload to Speak AI storage. After getting
the URL, PUT your file to it, then call upload_media with the S3 URL. For a
simpler workflow, use upload_local_file instead which handles all steps
automatically.
Parameters
get_signed_upload_url takes 3 parameters, 1 of them required.
| Name | Type | Required | Description |
|---|---|---|---|
filename |
string | Yes | Original filename including extension, e.g. “interview.mp4”. The extension decides audio vs video and the storage path, so it must match the real file: a video named “.mp3” is stored as audio and can never be analysed as video. |
mediaType |
enum | No | Type of media: “audio” or “video”. It decides the storage path, so it has to match the real file. Send it whenever the user has told you which they want, or when the filename extension does not reflect the real container. Omit it to derive the type from the extension, which is the only evidence available here because the bytes do not exist yet. |
mimeType |
string | No | MIME type, e.g. “video/mp4”. Omit to derive it from the filename extension. |
Behaviour
The Speak AI MCP server publishes these behaviour hints for get_signed_upload_url.
- Only reads data. Does not modify your workspace.
- Does not delete or overwrite existing data.
- Repeating an identical call can have an extra effect.
- Stays inside Speak AI. Does not reach other systems.
Related
- Media library lists the rest of the Media library category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.