v0.20.0¶
Release date: 2026-11-17
This release checks wording attributed to a recording against the recording itself. Several speech-to-text engines hear a short clip around the quotation, and fixed rules decide whether they all heard it, agree on a correction, or disagree on a word that matters. One engine's transcript can't show which of its words are wrong; several engines hearing the same clip can.
Highlights¶
- Quotations checked against audio —
stt/verifylocates a quotation in a timed transcript, clips it, has several engines hear the clip and compares what they heard - Deterministic decisions —
agreed,corrected,disputed,notFoundorinsufficient, from token kinds and fixed rules, so the same hearings always give the same result - Clips for speech-to-text —
audio/clipcuts 16 kHz mono WAV with ffmpeg
Added¶
Verification (stt/verify/)¶
Normalizeturns text into comparable tokens: lower case, punctuation removed, contractions expanded, number words as digits, "%" as "percent", fillers dropped. Each token has a kind:number,negation,term,name,functionorcontent; every kind exceptfunctionis substantive.AlignandAlignWithinuse an affine-gap alignment suited to quotations: a skipped run of the speaker's words costs about one edit, a misheard word costs less when it is spelled like the quoted one, and a quoted word left out costs most. Words heard across a marked elision cost nothing.Locatefinds wording in a timed transcript, with a score and the number of quoted words missing at each edge.Comparedecides from several hearings:
| Decision | When |
|---|---|
agreed |
Every engine heard every quoted word, apart from function words where most agree with the quotation |
corrected |
The engines agree with each other but not with the quotation |
disputed |
They disagree on a substantive word, or none heard the first or last words |
notFound |
The quotation could not be located |
insufficient |
Too few engines produced a transcript |
Stutters ("to, to") are ignored, split words ("work flow") are joined,
and CompareOptions.Aliases accepts other ways of saying a term.
- TranscribeAll has several engines transcribe one clip at once. Key words
go only to engines not marked NoKeywords, and it returns
ErrAllEnginesUseKeywords rather than give them to every engine.
- Verifier.VerifyQuotes checks quotations end to end and returns a
Report with the recording's SHA-256, the engines, the clip times and
every decision. When no engine hears a quotation's first or last words,
it widens the clip and listens again, up to two times.
- Search looks for phrases across independent transcripts. Its statement
says only how many transcripts have each phrase, never that the
recording lacks it.
v := verify.Verifier{
Engines: []verify.Engine{
{Name: "deepgram", Provider: deepgram},
{Name: "elevenlabs", Provider: elevenlabs},
{Name: "openai", Provider: openai, NoKeywords: true},
},
}
report, err := v.VerifyQuotes(ctx, "episode.mp3", verify.WordsFromTranscript(t), "deepgram",
[]verify.Quote{{ID: "q1", Text: "we can have the model run all the tests"}})
Clips (audio/clip/)¶
Clip(ctx, path, start, end)returns 16 kHz mono WAV. ffmpeg must be onPATH;ErrNoFFmpegreports when it isn't. The WAV header carries real sizes, which ffmpeg leaves unset when writing to a pipe and some services reject.
Schema (schema/)¶
VerifyReportV1Schema, the verify report's JSON Schema, generated from its Go types bygo run schema/gen/main.go. A test fails when the committed schema is out of date.
Documentation¶
Dependencies¶
- Requires
github.com/invopop/jsonschemav0.14.0, to generate the verify report schema. - Module dependencies updated.
Compatibility¶
No breaking changes. The new packages are additive.