Skip to content

fix(vscode): default speech to text to Parakeet #13162

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
marius-kilocode merged 2 commits into from
Aug 17, 2026
Merged

fix(vscode): default speech to text to Parakeet #13162

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8ad3f90
fix(vscode): default speech to text to parakeet
marius-kilocode Aug 17, 2026
6967211
test(vscode): update speech to text fallback
marius-kilocode Aug 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/dynamic-speech-to-text-models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"kilo-code": patch
---

Use NVIDIA Parakeet TDT 0.6B v3 as the default speech-to-text model while retaining dynamic model discovery and offline fallback support.
10 changes: 5 additions & 5 deletions packages/kilo-vscode/src/speech-to-text/models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,11 @@ export interface SpeechToTextModelDef {
}

const models: SpeechToTextModelDef[] = [
{
id: "nvidia/parakeet-tdt-0.6b-v3",
Comment thread
marius-kilocode marked this conversation as resolved.
label: "Parakeet TDT 0.6B v3",
provider: "NVIDIA",
},
{
id: "openai/whisper-large-v3-turbo",
label: "Whisper Large V3 Turbo",
Expand Down Expand Up @@ -38,11 +43,6 @@ const models: SpeechToTextModelDef[] = [
label: "Chirp 3",
provider: "Google",
},
{
id: "nvidia/parakeet-tdt-0.6b-v3",
label: "Parakeet TDT 0.6B v3",
provider: "NVIDIA",
},
]

export const SPEECH_TO_TEXT_MODELS: readonly SpeechToTextModelDef[] = models
Expand Down
2 changes: 1 addition & 1 deletion packages/kilo-vscode/tests/unit/speech-to-text-catalog.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,6 @@ describe("speech-to-text discovery", () => {
it("rejects empty or malformed catalogs so callers can use the static fallback", () => {
expect(parseSpeechToTextCatalog([])).toBeUndefined()
expect(parseSpeechToTextCatalog({ data: [] })).toBeUndefined()
expect(DEFAULT_SPEECH_TO_TEXT_MODEL.id).toBe("openai/whisper-large-v3-turbo")
expect(DEFAULT_SPEECH_TO_TEXT_MODEL.id).toBe("nvidia/parakeet-tdt-0.6b-v3")
})
})
4 changes: 2 additions & 2 deletions packages/kilo-vscode/tests/unit/speech-to-text-models-sync.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,8 @@ import {
} from "../../src/speech-to-text/models"

describe("speech-to-text model catalog", () => {
it("uses Whisper Large V3 Turbo as the fallback default", () => {
expect(DEFAULT_SPEECH_TO_TEXT_MODEL.id).toBe("openai/whisper-large-v3-turbo")
it("uses NVIDIA Parakeet TDT 0.6B v3 as the fallback default", () => {
expect(DEFAULT_SPEECH_TO_TEXT_MODEL.id).toBe("nvidia/parakeet-tdt-0.6b-v3")
expect(DEFAULT_SPEECH_TO_TEXT_MODEL.id).toBe(SPEECH_TO_TEXT_MODELS[0]?.id)
})

Expand Down
Loading