docs: restrict voice input to WAV attachments

1 files changed, 10 insertions, 8 deletions

diff --git a/docs/superpowers/specs/2026-09-18-voice-input-design.md b/docs/superpowers/specs/2026-09-18-voice-input-design.md
index aeb240f..58aaf58 100644
--- a/docs/superpowers/specs/2026-09-18-voice-input-design.md
+++ b/docs/superpowers/specs/2026-09-18-voice-input-design.md
@@ -115,14 +115,16 @@ the raw base64 payload. The image field stays a `data:` URL because images use
 `image_url`; llama.cpp wants audio as `{"data": "<raw base64>", "format":
 "wav"}`, with no `data:` prefix.
 
-- `classify()` recognises the common audio types (`audio/wav`, `audio/x-wav`,
-  `audio/mpeg`, `audio/flac`, `audio/ogg`) and the extensions `.wav`, `.mp3`,
-  `.flac`, `.ogg`, `.m4a`. Recording is the headline feature, but a dropped
-  audio file is accepted and treated identically: same kind, same content
-  part, same send gate. Sharing the kind means classification and the content
-  builder have one audio path instead of two, so the file case costs nothing.
-  A file the user dropped is theirs and is never deleted; only the recorder's
-  temp clip is discarded after send.
+- `classify()` recognises WAV: the `audio/wav` and `audio/x-wav` types and
+  the `.wav` extension. Only WAV, because the content part's `format` field
+  is a fixed `"wav"` and sending MP3 or FLAC bytes under that label would
+  misrepresent them. A recorder produces WAV anyway. Recording is the
+  headline feature, but a dropped `.wav` file is accepted and treated
+  identically: same kind, same content part, same send gate. Sharing the kind
+  means classification and the content builder have one audio path instead of
+  two. A file the user dropped is theirs and is never deleted; only the
+  recorder's temp clip is discarded after send. (ponytail: WAV only; derive
+  the format per file if another type is ever needed.)
 - `load_attachment()` fills `b64` for an audio file.
 - `build_user_content()` gains an audio branch, parallel to the image branch.
   It returns the multi-part array when either images or audio are present: