Files
simstudioai--sim/apps/sim/tools/tts/google.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

146 lines
4.2 KiB
TypeScript

import type { GoogleTtsParams, TtsBlockResponse } from '@/tools/tts/types'
import type { ToolConfig } from '@/tools/types'
export const googleTtsTool: ToolConfig<GoogleTtsParams, TtsBlockResponse> = {
id: 'tts_google',
name: 'Google Cloud TTS',
description: 'Convert text to speech using Google Cloud Text-to-Speech',
version: '1.0.0',
params: {
text: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The text content to convert to speech (e.g., "Hello, welcome to our service!")',
},
apiKey: {
type: 'string',
required: true,
visibility: 'user-only',
description: 'Google Cloud API key',
},
voiceId: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description:
'Google Cloud voice identifier (e.g., "en-US-Neural2-A", "en-US-Wavenet-D", "en-GB-Neural2-B")',
},
languageCode: {
type: 'string',
required: true,
visibility: 'user-or-llm',
description:
'BCP-47 language code for speech synthesis (e.g., "en-US", "es-ES", "fr-FR", "de-DE")',
},
gender: {
type: 'string',
required: false,
visibility: 'user-only',
description: 'Voice gender (MALE, FEMALE, NEUTRAL)',
},
audioEncoding: {
type: 'string',
required: false,
visibility: 'user-only',
description: 'Audio encoding (LINEAR16, MP3, OGG_OPUS, MULAW, ALAW)',
},
speakingRate: {
type: 'number',
required: false,
visibility: 'user-or-llm',
description:
'Speaking rate multiplier from 0.25 to 2.0 (e.g., 0.5 for slower, 1.0 for normal, 1.5 for faster)',
},
pitch: {
type: 'number',
required: false,
visibility: 'user-only',
description: 'Voice pitch (-20.0 to 20.0, default: 0.0)',
},
volumeGainDb: {
type: 'number',
required: false,
visibility: 'user-only',
description: 'Volume gain in dB (-96.0 to 16.0)',
},
sampleRateHertz: {
type: 'number',
required: false,
visibility: 'user-only',
description: 'Sample rate in Hz',
},
effectsProfileId: {
type: 'array',
required: false,
visibility: 'user-only',
description: "Effects profile (e.g., ['headphone-class-device'])",
},
},
request: {
url: '/api/tools/tts/unified',
method: 'POST',
headers: () => ({
'Content-Type': 'application/json',
}),
body: (
params: GoogleTtsParams & {
_context?: { workspaceId?: string; workflowId?: string; executionId?: string }
}
) => ({
provider: 'google',
text: params.text,
apiKey: params.apiKey,
voiceId: params.voiceId,
languageCode: params.languageCode,
gender: params.gender,
audioEncoding: params.audioEncoding || 'MP3',
speakingRate: params.speakingRate ?? 1.0,
pitch: params.pitch ?? 0.0,
volumeGainDb: params.volumeGainDb,
sampleRateHertz: params.sampleRateHertz,
effectsProfileId: params.effectsProfileId,
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 || 'TTS generation failed',
output: {
audioUrl: '',
},
}
}
return {
success: true,
output: {
audioUrl: data.audioUrl,
audioFile: data.audioFile,
duration: data.duration,
characterCount: data.characterCount,
format: data.format,
provider: data.provider,
},
}
},
outputs: {
audioUrl: { type: 'string', description: 'URL to the generated audio file' },
audioFile: { type: 'file', description: 'Generated audio file object' },
duration: { type: 'number', description: 'Audio duration in seconds' },
characterCount: { type: 'number', description: 'Number of characters processed' },
format: { type: 'string', description: 'Audio format' },
provider: { type: 'string', description: 'TTS provider used' },
},
}