Files
simstudioai--sim/apps/sim/tools/stt/gemini.ts
T
wehub-resource-sync d25d482dc2
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:20:55 +08:00

155 lines
4.4 KiB
TypeScript

import type { SttParams, SttResponse, SttV2Params } from '@/tools/stt/types'
import type { ToolConfig } from '@/tools/types'
export const geminiSttTool: ToolConfig<SttParams, SttResponse> = {
id: 'stt_gemini',
name: 'Google Gemini STT',
description: 'Transcribe audio to text using Google Gemini with multimodal capabilities',
version: '1.0.0',
params: {
provider: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'STT provider (gemini)',
},
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Google API key',
},
model: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Gemini model to use (default: gemini-2.5-flash)',
},
audioFile: {
type: 'file',
required: false,
visibility: 'user-only',
description: 'Audio or video file to transcribe (e.g., MP3, WAV, M4A, WEBM)',
},
audioFileReference: {
type: 'file',
required: false,
visibility: 'user-only',
description: 'Reference to audio/video file from previous blocks',
},
audioUrl: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'URL to audio or video file',
},
language: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Language code (e.g., "en", "es", "fr") or "auto" for auto-detection',
},
timestamps: {
type: 'string',
required: false,
visibility: 'user-only',
description: 'Timestamp granularity: none, sentence, or word',
},
},
request: {
url: '/api/tools/stt',
method: 'POST',
headers: () => ({
'Content-Type': 'application/json',
}),
body: (
params: SttParams & {
_context?: { workspaceId?: string; workflowId?: string; executionId?: string }
}
) => ({
provider: 'gemini',
apiKey: params.apiKey,
model: params.model,
audioFile: params.audioFile,
audioFileReference: params.audioFileReference,
audioUrl: params.audioUrl,
language: params.language || 'auto',
timestamps: params.timestamps || 'none',
workspaceId: params._context?.workspaceId,
workflowId: params._context?.workflowId,
executionId: params._context?.executionId,
}),
},
transformResponse: async (response: Response) => {
const data = await response.json()
if (!response.ok || data.error) {
return {
success: false,
error: data.error || 'Transcription failed',
output: {
transcript: '',
},
}
}
return {
success: true,
output: {
transcript: data.transcript,
segments: data.segments,
language: data.language,
duration: data.duration,
confidence: data.confidence,
},
}
},
outputs: {
transcript: { type: 'string', description: 'Full transcribed text' },
segments: { type: 'array', description: 'Timestamped segments' },
language: { type: 'string', description: 'Detected or specified language' },
duration: { type: 'number', description: 'Audio duration in seconds' },
confidence: { type: 'number', description: 'Overall confidence score' },
},
}
const geminiSttV2Params = {
provider: geminiSttTool.params.provider,
apiKey: geminiSttTool.params.apiKey,
model: geminiSttTool.params.model,
audioFile: geminiSttTool.params.audioFile,
audioFileReference: geminiSttTool.params.audioFileReference,
language: geminiSttTool.params.language,
timestamps: geminiSttTool.params.timestamps,
} satisfies ToolConfig['params']
export const geminiSttV2Tool: ToolConfig<SttV2Params, SttResponse> = {
...geminiSttTool,
id: 'stt_gemini_v2',
name: 'Gemini STT',
params: geminiSttV2Params,
request: {
...geminiSttTool.request,
body: (
params: SttV2Params & {
_context?: { workspaceId?: string; workflowId?: string; executionId?: string }
}
) => ({
provider: 'gemini',
apiKey: params.apiKey,
model: params.model,
audioFile: params.audioFile,
audioFileReference: params.audioFileReference,
language: params.language || 'auto',
timestamps: params.timestamps || 'none',
workspaceId: params._context?.workspaceId,
workflowId: params._context?.workflowId,
executionId: params._context?.executionId,
}),
},
}