speaker-recognizer

# Speaker Recognizer Each mic transcript is prefixed `Speaker - Name:` when recognized, or `Unknown Speaker: [voice:voice_N] ... (audio save[d] at <path>...)` otherwise. The audio path is the WAV of whoever spoke this turn — use it (with paths from prior same-tag turns when needed) to enroll on `POST /speaker/enroll`. **Self-enrollment only** — never enroll one person's voice under another person's name. ## Decision matrix — pick ONE action per turn | Signals in current turn | Prior same-tag turns? | Action | |---|---|---| | `Unknown Speaker:` + path + name + ≥25 words | — | **Enroll now** with current path only. | | `Unknown Speaker:` + path + name + <25 words | ≥1 prior path same `[voice:N]` | **Enroll now** with all same-tag paths (oldest→newest). | | `Unknown Speaker:` + path + name + <25 words | none | Ask one follow-up: "say your name + ~25–30 words". | | `Unknown Speaker:` + path + NO name + <25 words | none | Ask one follow-up. | | `Unknown Speaker:` + path + NO name | ≥1 prior path same `[voice:N]` (still no name) | Reply with a SHORT ack ("Mm, nghe rồi" / "Got it"). NEVER NO_REPLY. Don't re-ask. | | `Speaker - <Name>:` | — | Already identified — skill not needed. | | "who do you know?" / "list voices" | — | `GET /speaker/list`. | | "forget my voice" / "remove Alex" | — | `POST /speaker/remove`. | | Telegram voice note + intro | — | Convert to WAV + enroll with Telegram fields. | | Telegram voice note + "who is this?" | — | `POST /speaker/recognize`. | When in d...