diff --git a/README.md b/README.md index f551b674f..c34cb8d45 100644 --- a/README.md +++ b/README.md @@ -163,7 +163,7 @@ listed under [In progress](#in-progress), and what comes next under [Planned](#p ([Web clipper](docs/web-clipper.md), [setting it up](docs/web-clipper.md#setting-it-up), [the assistant in your browser](docs/browser-assistant.md); [checks](docs/requirements.md#clip-from-the-browser)) - **Understand it.** Transcription, which can expect the names your namespace knows (off by default), people - recognised by voice (long recordings go to a speech provider in pieces that fit its limits), text on screen and in scans, faces (off by default), NSFW pictures flagged by a model on your own + recognised by voice (an owner can keep voices to each recording instead; long recordings go to a speech provider in pieces that fit its limits), text on screen and in scans, faces (off by default), NSFW pictures flagged by a model on your own server (off by default, per namespace), low quality images enhanced before they're read (off by default), entities and topics in a knowledge graph you can explore, query with Cypher or SPARQL, and see as it was at any version, where every source, sensor, person and agent is a node linked to what it diff --git a/changelog.d/voices-off.md b/changelog.d/voices-off.md new file mode 100644 index 000000000..12e830419 --- /dev/null +++ b/changelog.d/voices-off.md @@ -0,0 +1,3 @@ +- **Voice recognition off, per namespace.** An owner can turn off People › Recognise voices across recordings: voices + are still told apart in each recording, but no voiceprint is kept and the namespace's voiceprints are deleted + ([People and namespaces](docs/processing.md#people-and-namespaces)). diff --git a/docs/processing.md b/docs/processing.md index d3f7fe96d..e4470b15d 100644 --- a/docs/processing.md +++ b/docs/processing.md @@ -195,6 +195,13 @@ as the same person (and unlink them), and with `speakers.cross_namespace: sugges as dashed edges and People lists them with how alike the voices are. Saying a suggested pair is "not the same", in one namespace or across two, removes the suggestion for good. +**Voice recognition off.** Voiceprints are biometric data. An owner can turn off People › Recognise voices across +recordings for their namespace (`PUT /api/v1/namespaces//voices/mode {"mode": "separate"}`; `GET /speakers` says +which is on as `voices`). Voices are then still told apart inside each recording, but no voiceprint is kept and nobody +is matched across recordings or namespaces. Turning it off deletes the namespace's voiceprints (each person's, each +appearance's and those kept for undoing a merge) and the matches waiting for review, and is audited as `voices.mode`; +names, transcripts and who spoke when stay. Turning it back on recognises people in recordings diarized after that. + ## Knowledge graph Nodes are people and named things. Edges are: diff --git a/docs/requirements.md b/docs/requirements.md index 07d79110b..0fcb54870 100644 --- a/docs/requirements.md +++ b/docs/requirements.md @@ -196,6 +196,7 @@ request, to another check that proves the same thing; loosening a requirement or | Transcription that expects the names the namespace knows (custom vocabulary, named people, defined entities, names people fixed), off by default | [test_speech.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_speech.py) `test_the_namespaces_own_names_go_to_the_engine` | | Transcription by a local engine (SenseVoice, Whisper), run in CI | No check yet ([#486](https://github.com/adeelahmad/lense/issues/486)) | | People recognised by voice; long recordings sent to a speech provider in pieces that fit its limits | [test_voices.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_voices.py) `test_match_suggest_merge_undo_link`; [test_speech.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_speech.py) `test_a_long_recording_goes_in_pieces_and_comes_back_whole`, `test_a_piece_too_large_to_send_is_halved` | +| An owner turns voice recognition off for a namespace: voices told apart in each recording only, its voiceprints deleted | [test_voice_mode.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_voice_mode.py) `test_voices_can_be_told_apart_without_being_recognised` | | Text on screen and in scans | [test_video.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_video.py) `test_shots_text_search_chat_and_iiif`; [test_documents.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_documents.py) `test_scans_and_images_are_read_by_ocr`; [test_ocr.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_ocr.py) `test_a_video_read_by_doctr_and_without_it` | | Faces, off by default | [test_video.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_video.py) `test_people_on_screen`, `test_shots_text_search_chat_and_iiif`; [test_video.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/domain/test_video.py) `test_face_modes` | | NSFW pictures flagged by a model on your own server, off by default, per namespace | [test_nsfw.py](https://github.com/adeelahmad/lense/blob/main/fastapi_backend/tests/api/test_nsfw.py) `test_off_by_default_nothing_is_fetched_or_classified`, `test_a_namespace_classifies_flags_blurs_and_hides`; [nsfw.test.tsx](https://github.com/adeelahmad/lense/blob/main/nextjs-frontend/__tests__/nsfw.test.tsx) | diff --git a/fastapi_backend/app/api/v1/routes/speakers.py b/fastapi_backend/app/api/v1/routes/speakers.py index 78efff231..a4413bcf9 100644 --- a/fastapi_backend/app/api/v1/routes/speakers.py +++ b/fastapi_backend/app/api/v1/routes/speakers.py @@ -20,6 +20,7 @@ SpeakerPair, SpeakerRecording, SpeakerRename, + VoiceMode, ) router = APIRouter(tags=["speakers"]) @@ -98,10 +99,26 @@ def list_speakers(ns: str, acl: Acl, user: CurrentUser, db: Db, cfg: Cfg) -> Spe if nid in (x["asp"], x["bsp"]) ] return SpeakerDirectory.model_validate( - {"speakers": spk.list_speakers(db, nid), "merges": merges, "links": links, "cross": _cross(db, cfg, nid, set(acl.roles))} + { + "speakers": spk.list_speakers(db, nid), + "merges": merges, + "links": links, + "cross": _cross(db, cfg, nid, set(acl.roles)), + "voices": spk.voice_mode(db, nid), + } ) +@router.put("/namespaces/{name}/voices/mode") +def set_namespace_voice_mode(name: str, body: VoiceMode, user: Writer, acl: Acl, db: Db) -> Ok: + """Recognise voices across the namespace's recordings (the default), or only tell them apart in each one + (separate), which deletes its voiceprints and the matches waiting for review. Owners only.""" + nid = acl.namespace(name, "manage") + spk.set_voice_mode(db, nid, body.mode, user.email) + auth.audit(db, user.as_audit(), "voices.mode", name, {"mode": body.mode}) + return Ok() + + @router.get("/speakers/{sid}/recordings") def list_speaker_recordings(sid: int, acl: Acl, user: CurrentUser, db: Db) -> list[SpeakerRecording]: acl.need(speaker_space(db, sid)) diff --git a/fastapi_backend/app/domain/speakers.py b/fastapi_backend/app/domain/speakers.py index b174367cb..456de9c87 100644 --- a/fastapi_backend/app/domain/speakers.py +++ b/fastapi_backend/app/domain/speakers.py @@ -3,6 +3,10 @@ Speaker ids belong to one namespace and are never merged across namespaces. Across namespaces the archive only records links: ones you declare, and (optionally) voice matches it suggests as graph edges. + +A namespace's owner can turn voice recognition off (`voice_mode` separate): voices are still told apart inside each +recording, but no voiceprint is kept and nobody is matched across recordings. Turning it off deletes the namespace's +voiceprints and the matches waiting for review. """ from __future__ import annotations @@ -184,6 +188,33 @@ def voice_print(signal, segs, embed, seconds=60): # ---------- the namespace registry ---------- R = store.R +VOICE_MODES = ("recognize", "separate") + + +def voice_mode(db, nid): + """recognize (the default: voiceprints kept, people matched across recordings) or separate (told apart in each + recording only).""" + return (db.one("SELECT voices_mode FROM $s", s=R("space", int(nid))) or {}).get("voices_mode") or "recognize" + + +def set_voice_mode(db, nid, mode, user=None): + """Recognise voices across recordings, or only tell them apart in each one. Separate deletes the namespace's + voiceprints (people's, each appearance's and those kept for undoing a merge) and its suggested matches: there is + nothing left to match with. Recognising again starts from the recordings diarized after it.""" + if mode not in VOICE_MODES: + raise ValueError(f"voice mode is one of {', '.join(VOICE_MODES)}") + db.q("UPDATE $s MERGE $p", s=R("space", int(nid)), p={"voices_mode": mode, "voices_set_by": user, "voices_set_at": store.now()}) + if mode == "separate": + db.run( + [ + "UPDATE speaker SET embedding = NONE, n_obs = 0 WHERE space = $s", + "UPDATE appearance SET embedding = NONE WHERE space = $s", + "DELETE suggestion WHERE space = $s", + # the voiceprints kept for undoing a merge too + "UPDATE merge SET snapshot.speaker.embedding = NONE, snapshot.dst.embedding = NONE WHERE space = $s", + ], + s=int(nid), + ) def _vec(v): @@ -316,6 +347,9 @@ def diarize_one(db, cfg, rid, log=print): vp = voice_print(sig, g, emb, cfg["speakers"]["sample_seconds"]) if vp is not None: prints[l] = vp + keep = voice_mode(db, r["space"]) == "recognize" + if not keep: # told apart in this recording only: no voiceprint kept, nobody matched + prints = {} ids = match(db, cfg, r["space"], prints) if prints else {} for l in groups: if l not in ids: diff --git a/fastapi_backend/app/schemas/speakers.py b/fastapi_backend/app/schemas/speakers.py index 63d40ec74..b22453f6c 100644 --- a/fastapi_backend/app/schemas/speakers.py +++ b/fastapi_backend/app/schemas/speakers.py @@ -1,6 +1,6 @@ from __future__ import annotations -from typing import Any +from typing import Any, Literal from pydantic import Field @@ -69,6 +69,17 @@ class SpeakerDirectory(ResponseModel): description="likely the same person in another shared namespace you can read (speakers.cross_namespace: suggest), " "best first; not linked, and not marked as different", ) + voices: Literal["recognize", "separate"] = Field( + "recognize", + description="recognize: voiceprints kept and people matched across recordings; separate: voices told apart in " + "each recording only (PUT /namespaces/{name}/voices/mode)", + ) + + +class VoiceMode(RequestModel): + mode: Literal["recognize", "separate"] = Field( + description="recognize, or separate: voices told apart in each recording only, the namespace's voiceprints deleted" + ) class SpeakerRecording(ResponseModel): diff --git a/fastapi_backend/tests/api/test_voice_mode.py b/fastapi_backend/tests/api/test_voice_mode.py new file mode 100644 index 000000000..35be68d1b --- /dev/null +++ b/fastapi_backend/tests/api/test_voice_mode.py @@ -0,0 +1,66 @@ +"""Voice recognition per namespace (speakers.voice_mode): on by default; off, voices are told apart in each recording +only, and the namespace's voiceprints are deleted.""" + +from __future__ import annotations + +import numpy as np + +from app.domain import ingest, speakers, store +from tests.helpers import login, make_user, unit + +R = store.R + + +def _recording(db, nid, n): + rid = db.next_id("recording") + db.q( + "CREATE $r CONTENT $d", r=R("recording", rid), d={"space": nid, "fingerprint": f"fp{n}", "status": "transcribed", "source": "audio"} + ) + segs = [{"t0": 0, "t1": 1000, "text": "hello"}, {"t0": 1000, "t1": 2000, "text": "hi"}] + db.q("INSERT INTO segment $s", s=ingest.segment_rows(rid, nid, segs)) + for i, who in enumerate(("A", "B")): + db.q("UPDATE segment SET provider_speaker = $p WHERE recording = $r AND idx = $i", p=who, r=rid, i=i) + return rid + + +def test_voices_can_be_told_apart_without_being_recognised(client, db, cfg, monkeypatch): + rng = np.random.default_rng(5) + prints = {"A": unit(rng.normal(size=192)), "B": unit(rng.normal(size=192))} + monkeypatch.setattr(ingest, "audio_path", lambda *a, **k: "unused.wav") + monkeypatch.setattr(ingest, "decode", lambda *a, **k: np.zeros(16000, dtype=np.float32)) + monkeypatch.setattr(speakers, "get_embedder", lambda cfg, log=None: object()) + monkeypatch.setattr(speakers, "voice_print", lambda sig, g, emb, s: (prints[g[0]["provider_speaker"]], 30.0)) + nid = store.ns_id(db, "pods") + + def who(rid): + return sorted(db.values("SELECT VALUE speaker FROM appearance WHERE recording = $r", r=rid)) + + first, second = _recording(db, nid, 1), _recording(db, nid, 2) + speakers.diarize_one(db, cfg, first, log=lambda *a: None) + speakers.diarize_one(db, cfg, second, log=lambda *a: None) + assert who(first) == who(second) # recognised: the same two people + assert db.values("SELECT VALUE embedding FROM speaker WHERE space = $s AND embedding != NONE", s=nid) + + make_user(db, "own@x.io", "owner password 1", roles={"pods": "owner"}) + make_user(db, "ed@x.io", "editor password 1", roles={"pods": "editor"}) + ho, he = login(client, "own@x.io", "owner password 1"), login(client, "ed@x.io", "editor password 1") + assert client.get("/api/v1/speakers", params={"ns": "pods"}, headers=ho).json()["voices"] == "recognize" + url = "/api/v1/namespaces/pods/voices/mode" + assert client.put(url, headers=he, json={"mode": "separate"}).status_code == 403 # owners only + assert client.put(url, headers=ho, json={"mode": "never"}).status_code == 422 + assert client.put(url, headers=ho, json={"mode": "separate"}).status_code == 200 + assert client.get("/api/v1/speakers", params={"ns": "pods"}, headers=ho).json()["voices"] == "separate" + assert db.values("SELECT VALUE embedding FROM speaker WHERE space = $s AND embedding != NONE", s=nid) == [] + assert db.values("SELECT VALUE embedding FROM appearance WHERE space = $s AND embedding != NONE", s=nid) == [] + assert db.one("SELECT detail FROM audit_log WHERE action = 'voices.mode'")["detail"] == {"mode": "separate"} + + third = _recording(db, nid, 3) + speakers.diarize_one(db, cfg, third, log=lambda *a: None) + assert len(who(third)) == 2 and not set(who(third)) & set(who(first)) # told apart, matched with nobody + assert db.values("SELECT VALUE embedding FROM speaker WHERE space = $s AND embedding != NONE", s=nid) == [] + + assert client.put(url, headers=ho, json={"mode": "recognize"}).status_code == 200 + fourth, fifth = _recording(db, nid, 4), _recording(db, nid, 5) + speakers.diarize_one(db, cfg, fourth, log=lambda *a: None) + speakers.diarize_one(db, cfg, fifth, log=lambda *a: None) + assert who(fourth) == who(fifth) # recognising again, from then on diff --git a/nextjs-frontend/app/openapi-client/index.ts b/nextjs-frontend/app/openapi-client/index.ts index c806080de..03180d21b 100644 --- a/nextjs-frontend/app/openapi-client/index.ts +++ b/nextjs-frontend/app/openapi-client/index.ts @@ -3569,6 +3569,11 @@ export type { SetNamespaceFacesModeErrors, SetNamespaceFacesModeResponse, SetNamespaceFacesModeResponses, + SetNamespaceVoiceModeData, + SetNamespaceVoiceModeError, + SetNamespaceVoiceModeErrors, + SetNamespaceVoiceModeResponse, + SetNamespaceVoiceModeResponses, SetPolicyData, SetPolicyError, SetPolicyErrors, @@ -4339,6 +4344,7 @@ export type { VoiceInfoResponse, VoiceInfoResponses, VoiceList, + VoiceMode, VoiceOption, Watch, WatchCreate, diff --git a/nextjs-frontend/app/openapi-client/sdk.gen.ts b/nextjs-frontend/app/openapi-client/sdk.gen.ts index 37c981320..4ef2da8bf 100644 --- a/nextjs-frontend/app/openapi-client/sdk.gen.ts +++ b/nextjs-frontend/app/openapi-client/sdk.gen.ts @@ -1717,6 +1717,9 @@ import type { SetNamespaceFacesModeData, SetNamespaceFacesModeErrors, SetNamespaceFacesModeResponses, + SetNamespaceVoiceModeData, + SetNamespaceVoiceModeErrors, + SetNamespaceVoiceModeResponses, SetPolicyData, SetPolicyErrors, SetPolicyResponses, @@ -7852,6 +7855,25 @@ export class Speakers { }); } + /** + * Set Namespace Voice Mode + * + * Recognise voices across the namespace's recordings (the default), or only tell them apart in each one + * (separate), which deletes its voiceprints and the matches waiting for review. Owners only. + */ + public static setNamespaceVoiceMode( + options: Options, + ): RequestResult { + return (options.client ?? client).put({ + url: "/api/v1/namespaces/{name}/voices/mode", + ...options, + headers: { + "Content-Type": "application/json", + ...options.headers, + }, + }); + } + /** * List Speaker Recordings */ diff --git a/nextjs-frontend/app/openapi-client/types.gen.ts b/nextjs-frontend/app/openapi-client/types.gen.ts index c350e91af..4513629a4 100644 --- a/nextjs-frontend/app/openapi-client/types.gen.ts +++ b/nextjs-frontend/app/openapi-client/types.gen.ts @@ -25754,6 +25754,12 @@ export type SpeakerDirectory = { * likely the same person in another shared namespace you can read (speakers.cross_namespace: suggest), best first; not linked, and not marked as different */ cross?: Array; + /** + * Voices + * + * recognize: voiceprints kept and people matched across recordings; separate: voices told apart in each recording only (PUT /namespaces/{name}/voices/mode) + */ + voices?: "recognize" | "separate"; [key: string]: unknown; }; @@ -29008,6 +29014,18 @@ export type VoiceList = { [key: string]: unknown; }; +/** + * VoiceMode + */ +export type VoiceMode = { + /** + * Mode + * + * recognize, or separate: voices told apart in each recording only, the namespace's voiceprints deleted + */ + mode: "recognize" | "separate"; +}; + /** * VoiceOption */ @@ -40070,6 +40088,36 @@ export type ListSpeakersResponses = { export type ListSpeakersResponse = ListSpeakersResponses[keyof ListSpeakersResponses]; +export type SetNamespaceVoiceModeData = { + body: VoiceMode; + path: { + /** + * Name + */ + name: string; + }; + query?: never; + url: "/api/v1/namespaces/{name}/voices/mode"; +}; + +export type SetNamespaceVoiceModeErrors = { + /** + * Validation Error + */ + 422: HttpValidationError; +}; + +export type SetNamespaceVoiceModeError = SetNamespaceVoiceModeErrors[keyof SetNamespaceVoiceModeErrors]; + +export type SetNamespaceVoiceModeResponses = { + /** + * Successful Response + */ + 200: Ok; +}; + +export type SetNamespaceVoiceModeResponse = SetNamespaceVoiceModeResponses[keyof SetNamespaceVoiceModeResponses]; + export type ListSpeakerRecordingsData = { body?: never; path: { diff --git a/nextjs-frontend/components/speakers/speakers-page.tsx b/nextjs-frontend/components/speakers/speakers-page.tsx index 58229fcb5..bae5faf60 100644 --- a/nextjs-frontend/components/speakers/speakers-page.tsx +++ b/nextjs-frontend/components/speakers/speakers-page.tsx @@ -10,6 +10,7 @@ import { useNamespaceSpeakers } from "@/components/speakers/parts"; import { lastHeard, reviewPairs } from "@/components/speakers/derive"; import { Registry } from "@/components/speakers/registry"; import { ReviewQueue } from "@/components/speakers/review"; +import { VoiceMode } from "@/components/speakers/voice-mode"; import { Banner } from "@/components/ui/banner"; import { Button } from "@/components/ui/button"; import { Select } from "@/components/ui/field"; @@ -26,7 +27,7 @@ export function SpeakersPage() { const params = useSearchParams(); const router = useRouter(); const pathname = usePathname(); - const { namespaces, namespace: topNs } = useArchive(); + const { namespaces, namespace: topNs, can } = useArchive(); const ns = params.get("ns") && namespaces.some((n) => n.name === params.get("ns")) ? params.get("ns")! @@ -141,6 +142,7 @@ export function SpeakersPage() { Voiceprints are built from clean audio (Settings → Voice IDs). People without one are still matched, less reliably.

+ )} {dir.data && ns && tab === "review" && } diff --git a/nextjs-frontend/components/speakers/voice-mode.tsx b/nextjs-frontend/components/speakers/voice-mode.tsx new file mode 100644 index 000000000..825dafa1e --- /dev/null +++ b/nextjs-frontend/components/speakers/voice-mode.tsx @@ -0,0 +1,67 @@ +"use client"; + +import { useMutation, useQueryClient } from "@tanstack/react-query"; +import { useState } from "react"; + +import { Speakers } from "@/app/openapi-client"; +import { Button } from "@/components/ui/button"; +import { Dialog } from "@/components/ui/dialog"; +import { Switch } from "@/components/ui/field"; +import { useToast } from "@/components/ui/toast"; +import { data, useApiClient } from "@/lib/api/browser"; + +/** + * Whether the namespace recognises voices across its recordings (owners switch it). Turning it off deletes the + * namespace's voiceprints, which can't be undone, so that one asks first; turning it back on doesn't. + */ +export function VoiceMode({ ns, mode, canManage }: { ns: string; mode: "recognize" | "separate"; canManage: boolean }) { + const client = useApiClient(); + const qc = useQueryClient(); + const toast = useToast(); + const [asking, setAsking] = useState(false); + const save = useMutation({ + mutationFn: (to: "recognize" | "separate") => + data(Speakers.setNamespaceVoiceMode({ client, path: { name: ns }, body: { mode: to } })), + onSuccess: (_, to) => { + void qc.invalidateQueries({ queryKey: ["speakers", ns] }); + setAsking(false); + toast({ + title: to === "separate" ? "Voices are told apart in each recording only" : "Voices are recognised again", + tone: "green", + }); + }, + onError: (e: Error) => toast({ title: "Couldn’t change voice recognition", body: e.message, tone: "red" }), + }); + return ( +
+ (on ? save.mutate("recognize") : setAsking(true))} + label="Recognise voices across recordings" + /> +

+ {mode === "recognize" + ? "Each person’s voiceprint is kept so they’re found again in new recordings." + : "Voices are told apart in each recording, but no voiceprint is kept and nobody is matched across recordings."} + {!canManage && " Owners of this namespace can change it."} +

+ !save.isPending && setAsking(o)} + title="Stop recognising voices?" + description={`The voiceprints of everyone in ${ns} are deleted, and matches waiting for review go too. Names, transcripts and who spoke when stay. This can’t be undone; turning it back on recognises people from new recordings.`} + actions={ + <> + + + + } + /> +
+ ); +} diff --git a/nextjs-frontend/openapi.json b/nextjs-frontend/openapi.json index f5120647c..245e06a9e 100644 --- a/nextjs-frontend/openapi.json +++ b/nextjs-frontend/openapi.json @@ -16785,6 +16785,59 @@ } } }, + "/api/v1/namespaces/{name}/voices/mode": { + "put": { + "tags": [ + "speakers" + ], + "summary": "Set Namespace Voice Mode", + "description": "Recognise voices across the namespace's recordings (the default), or only tell them apart in each one\n(separate), which deletes its voiceprints and the matches waiting for review. Owners only.", + "operationId": "set_namespace_voice_mode", + "parameters": [ + { + "name": "name", + "in": "path", + "required": true, + "schema": { + "type": "string", + "title": "Name" + } + } + ], + "requestBody": { + "required": true, + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/VoiceMode" + } + } + } + }, + "responses": { + "200": { + "description": "Successful Response", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/Ok" + } + } + } + }, + "422": { + "description": "Validation Error", + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + } + } + } + } + }, "/api/v1/speakers/{sid}/recordings": { "get": { "tags": [ @@ -80431,6 +80484,16 @@ "type": "array", "title": "Cross", "description": "likely the same person in another shared namespace you can read (speakers.cross_namespace: suggest), best first; not linked, and not marked as different" + }, + "voices": { + "type": "string", + "enum": [ + "recognize", + "separate" + ], + "title": "Voices", + "description": "recognize: voiceprints kept and people matched across recordings; separate: voices told apart in each recording only (PUT /namespaces/{name}/voices/mode)", + "default": "recognize" } }, "additionalProperties": true, @@ -85949,6 +86012,25 @@ ], "title": "VoiceList" }, + "VoiceMode": { + "properties": { + "mode": { + "type": "string", + "enum": [ + "recognize", + "separate" + ], + "title": "Mode", + "description": "recognize, or separate: voices told apart in each recording only, the namespace's voiceprints deleted" + } + }, + "additionalProperties": false, + "type": "object", + "required": [ + "mode" + ], + "title": "VoiceMode" + }, "VoiceOption": { "properties": { "id": {