File size: 3,816 Bytes
f56a29b | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 | /**
* Single TTS Generation API
*
* Generates TTS audio for a single text string and returns base64-encoded audio.
* Called by the client in parallel for each speech action after a scene is generated.
*
* POST /api/generate/tts
*/
import { NextRequest } from 'next/server';
import { generateTTS } from '@/lib/audio/tts-providers';
import { resolveTTSApiKey, resolveTTSBaseUrl } from '@/lib/server/provider-config';
import type { TTSProviderId } from '@/lib/audio/types';
import { createLogger } from '@/lib/logger';
import { apiError, apiSuccess } from '@/lib/server/api-response';
import { validateUrlForSSRF } from '@/lib/server/ssrf-guard';
import { VOXCPM_AUTO_VOICE_ID, VOXCPM_TTS_PROVIDER_ID } from '@/lib/audio/voxcpm';
const log = createLogger('TTS API');
export const maxDuration = 30;
export async function POST(req: NextRequest) {
let ttsProviderId: string | undefined;
let ttsVoice: string | undefined;
let audioId: string | undefined;
try {
const body = await req.json();
const { text, ttsModelId, ttsSpeed, ttsApiKey, ttsBaseUrl, ttsProviderOptions } = body as {
text: string;
audioId: string;
ttsProviderId: TTSProviderId;
ttsModelId?: string;
ttsVoice: string;
ttsSpeed?: number;
ttsApiKey?: string;
ttsBaseUrl?: string;
ttsProviderOptions?: Record<string, unknown>;
};
ttsProviderId = body.ttsProviderId;
ttsVoice = body.ttsVoice;
audioId = body.audioId;
// Validate required fields
if (!text || !audioId || !ttsProviderId || !ttsVoice) {
return apiError(
'MISSING_REQUIRED_FIELD',
400,
'Missing required fields: text, audioId, ttsProviderId, ttsVoice',
);
}
// Reject browser-native TTS — must be handled client-side
if (ttsProviderId === 'browser-native-tts') {
return apiError('INVALID_REQUEST', 400, 'browser-native-tts must be handled client-side');
}
const voxcpmVoicePrompt =
typeof ttsProviderOptions?.voicePrompt === 'string' ? ttsProviderOptions.voicePrompt : '';
if (
ttsProviderId === VOXCPM_TTS_PROVIDER_ID &&
ttsVoice === VOXCPM_AUTO_VOICE_ID &&
!voxcpmVoicePrompt.trim()
) {
return apiError(
'VOXCPM_AUTO_VOICE_REQUIRES_CONTEXT',
400,
'VoxCPM Auto Voice requires agent context',
);
}
const clientBaseUrl = ttsBaseUrl || undefined;
if (clientBaseUrl) {
const ssrfError = await validateUrlForSSRF(clientBaseUrl);
if (ssrfError) {
return apiError('INVALID_URL', 403, ssrfError);
}
}
const apiKey = clientBaseUrl
? ttsApiKey || ''
: resolveTTSApiKey(ttsProviderId, ttsApiKey || undefined);
const baseUrl = clientBaseUrl
? clientBaseUrl
: resolveTTSBaseUrl(ttsProviderId, ttsBaseUrl || undefined);
// Build TTS config
const config = {
providerId: ttsProviderId as TTSProviderId,
modelId: ttsModelId,
voice: ttsVoice,
speed: ttsSpeed ?? 1.0,
apiKey,
baseUrl,
providerOptions: ttsProviderOptions,
};
log.info(
`Generating TTS: provider=${ttsProviderId}, model=${ttsModelId || 'default'}, voice=${ttsVoice}, audioId=${audioId}, textLen=${text.length}`,
);
// Generate audio
const { audio, format } = await generateTTS(config, text);
// Convert to base64
const base64 = Buffer.from(audio).toString('base64');
return apiSuccess({ audioId, base64, format });
} catch (error) {
log.error(
`TTS generation failed [provider=${ttsProviderId ?? 'unknown'}, voice=${ttsVoice ?? 'unknown'}, audioId=${audioId ?? 'unknown'}]:`,
error,
);
return apiError(
'GENERATION_FAILED',
500,
error instanceof Error ? error.message : String(error),
);
}
}
|