a780fc7bd5
All checks were successful
Deploy / deploy (push) Successful in 2m58s
Stage 2 of voice integration — centralizes TTS on the tablet so the
Python satellite no longer needs ElevenLabs credentials or mpv.
- app/api/voice/tts — POST {text, agent}, proxies to ElevenLabs
streaming endpoint with flash_v2_5 default, returns audio/mpeg.
Per-agent voice id via COSMO_TTS_VOICE / LUSYA_TTS_VOICE env.
- VoiceOverlay — on response/error events fetches TTS and plays via
HTMLAudioElement; on wake event stops playback (barge-in). Dismiss
timer extended by text length so long responses do not cut off.
- Autoplay caveat: browser may block first playback until user taps
anywhere on the page (FKB: enable Force Autoplay to bypass).
76 lines
2.1 KiB
TypeScript
76 lines
2.1 KiB
TypeScript
export const dynamic = 'force-dynamic'
|
|
export const runtime = 'nodejs'
|
|
|
|
import { NextResponse } from 'next/server'
|
|
|
|
const ELEVENLABS_BASE = 'https://api.elevenlabs.io/v1'
|
|
const DEFAULT_MODEL = 'eleven_flash_v2_5'
|
|
|
|
function getVoiceId(agent: string | undefined): string | null {
|
|
if (agent === 'lusya') return process.env.LUSYA_TTS_VOICE || null
|
|
return process.env.COSMO_TTS_VOICE || null
|
|
}
|
|
|
|
export async function POST(req: Request) {
|
|
const apiKey = process.env.ELEVENLABS_API_KEY
|
|
if (!apiKey) {
|
|
return NextResponse.json({ error: 'tts_not_configured' }, { status: 503 })
|
|
}
|
|
|
|
const body = await req.json().catch(() => null)
|
|
const text = typeof body?.text === 'string' ? body.text.trim() : ''
|
|
const agent = typeof body?.agent === 'string' ? body.agent : 'cosmo'
|
|
|
|
if (!text) {
|
|
return NextResponse.json({ error: 'text required' }, { status: 400 })
|
|
}
|
|
if (text.length > 4000) {
|
|
return NextResponse.json({ error: 'text too long (>4000)' }, { status: 400 })
|
|
}
|
|
|
|
const voiceId = getVoiceId(agent)
|
|
if (!voiceId) {
|
|
return NextResponse.json({ error: `no voice configured for agent=${agent}` }, { status: 503 })
|
|
}
|
|
|
|
const model = process.env.ELEVENLABS_MODEL || DEFAULT_MODEL
|
|
|
|
const upstream = await fetch(
|
|
`${ELEVENLABS_BASE}/text-to-speech/${encodeURIComponent(voiceId)}/stream?output_format=mp3_44100_64`,
|
|
{
|
|
method: 'POST',
|
|
headers: {
|
|
'xi-api-key': apiKey,
|
|
Accept: 'audio/mpeg',
|
|
'Content-Type': 'application/json',
|
|
},
|
|
body: JSON.stringify({
|
|
text,
|
|
model_id: model,
|
|
voice_settings: {
|
|
stability: 0.45,
|
|
similarity_boost: 0.75,
|
|
style: 0.25,
|
|
use_speaker_boost: true,
|
|
},
|
|
}),
|
|
}
|
|
)
|
|
|
|
if (!upstream.ok || !upstream.body) {
|
|
const errText = await upstream.text().catch(() => '')
|
|
return NextResponse.json(
|
|
{ error: `elevenlabs_${upstream.status}`, detail: errText.slice(0, 300) },
|
|
{ status: 502 }
|
|
)
|
|
}
|
|
|
|
return new Response(upstream.body, {
|
|
headers: {
|
|
'Content-Type': 'audio/mpeg',
|
|
'Cache-Control': 'no-store',
|
|
'X-Accel-Buffering': 'no',
|
|
},
|
|
})
|
|
}
|