Build a multilingual voice assistant

  you ──► ┌──────────────── Evergreen AI :40071 ────────────────┐
          │  session (criteria-picked model) + chat message      │
          └───────┬─────────────────────────────────────────────┘
                  │ answer text (JSON, ~20–60 s on local models)
                  ▼
          ┌──────────────── Linga :40065 ───────────────────────┐
          │  POST /v3/translation/translate                     │
          │  en-US ──► es-ES (via Evergreen, single-turn)       │
          └───────┬─────────────────────────────────────────────┘
                  │ translated text
                  ▼
  your voice ──► ┌────────────── Speech :40161 ──────────────────┐
  (WAV upload,   │  voice print  ──►  CDN path (registered once) │
   voice print)  │  text-to-speech {input, reference_voiceprint} │
                 └───────┬────────────────────────────────────────┘
                         │ audio/mpeg (your voice, Spanish words)
                         ▼
                       speaker

InayaLabs-website/docs-src/tutorials/_code/multilingual-voice-assistant/
├── voice_assistant.sh   ← the assembled driver (all checkpoints)
└── README.md            ← how to run it standalone

KEYS=(-H "x-api-key: ${INAYA_API_KEY}" -H "x-client-app-key: ${INAYA_APP_KEY}")
sign_in() {
  curl -sf -X POST "${AUTH_URL}/v3/auth/qa/login" "${KEYS[@]}" \
    -H "Content-Type: application/json" \
    -d "{\"device_id\": \"t04-device-01\", \"locale\": \"en-US\", \"tenant_id\": \"${TENANT_ID}\", \"username\": \"$1\"}" \
    | python3 -c 'import json,sys; print(json.load(sys.stdin)["token"])'
}
TOKEN=$(sign_in t04-amara)

SESS=$(curl -sf -m 180 -X POST "${EVG_URL}/v3/sessions" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d '{
        "system_prompt": "You are a concise community-garden assistant. Answer in one or two short sentences.",
        "temperature": 0.2,
        "required_modalities": ["Text"],
        "selection_criteria": [
          {"Model": {"optionality": "MustHave", "name": "Llama3_2_1B_Q4"}}
        ]
      }')
SESSION_ID=$(python3 -c 'import json,sys; print(json.load(sys.stdin)["ai_session_id"])' <<< "${SESS}")
echo "session ${SESSION_ID:0:16}… created"

REPLY=$(curl -sf -m 240 -X POST "${EVG_URL}/v3/sessions/${SESSION_ID}/chat-messages" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -F "user_message=What should we plant this week? It is late September.")
ANSWER=$(python3 -c 'import json,sys
d = json.load(sys.stdin)
assert d["author"] == "Assistant", d
print(d["content"][0]["Text"])' <<< "${REPLY}")
test -n "${ANSWER}" && echo "assistant: ${ANSWER}"
echo "${ANSWER}" | grep -qi "plant\|crop\|seed\|frost\|season" \
  && echo "checkpoint 1 passed: session answered a gardening question"

ES=$(curl -sf -m 180 -X POST "${LINGA_URL}/v3/translation/translate" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d "$(python3 - "$ANSWER" <<'EOF'
import json, sys
print(json.dumps({
  "source": {"locale": "en-US"},
  "target": {"locale": "es-ES"},
  "text": sys.argv[1]
}))
EOF
)")
TRANSLATED=$(python3 -c 'import json,sys
d = json.load(sys.stdin)
assert d["original_text"], d
print(d["translated_text"])' <<< "${ES}")
echo "es: ${TRANSLATED}"
python3 - "$TRANSLATED" <<'EOF'
import sys
t = sys.argv[1]
assert any(c in t.lower() for c in "áéíóúñ¿¡") or " " in t, t
print("checkpoint 2 passed: answer translated for the Spanish-speaking volunteers")
EOF

say -o /tmp/t04-voice.aiff \
  "Hi, this is Amara. I keep the community garden notes, and I speak three languages."
afconvert -f WAVE -d LEI16@22050 /tmp/t04-voice.aiff /tmp/t04-voice.wav

VP=$(curl -sf -m 300 -X POST "${SPEECH_URL}/v3/voice-prints" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -F "file=@/tmp/t04-voice.wav")
VOICEPRINT_PATH=$(python3 -c 'import json,sys; print(json.load(sys.stdin)["voice_print_wav_path"])' <<< "${VP}")
echo "voice print: ${VOICEPRINT_PATH}"
grep -q "^speech-service/voice-prints/" <<< "${VOICEPRINT_PATH}" \
  && echo "checkpoint 3 passed: voice print registered and persisted to the CDN"

curl -sf -m 320 -o /tmp/t04-es.mp3 \
  -X POST "${SPEECH_URL}/v3/text-to-speech" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d "$(python3 - "$TRANSLATED" "$VOICEPRINT_PATH" <<'EOF'
import json, sys
print(json.dumps({
  "input": sys.argv[1],
  "reference_voiceprint_path": sys.argv[2]
}))
EOF
)"

python3 - <<'EOF'
data = open("/tmp/t04-es.mp3", "rb").read()
assert data[:3] == b"ID3" or data[:2] in (b"\xff\xfb", b"\xff\xf3", b"\xff\xf2"), data[:16]
print(f"audio: {len(data)} bytes, MP3 magic confirmed")
EOF
DUR=$(ffprobe -v error -show_entries format=duration -of csv=p=0 /tmp/t04-es.mp3)
python3 -c "d=float('${DUR}'); assert d > 1.0, d; print(f'checkpoint 4 passed: {d:.1f}s of Spanish speech synthesized in the registered voice')"

pkill -x linga-service && echo "linga-service killed"

curl -s -o /dev/null --max-time 5 \
  -X POST "${LINGA_URL}/v3/translation/translate" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d '{"source":{"locale":"en-US"},"target":{"locale":"ar-SA"},"text":"Water the tomatoes twice a week."}' \
  || echo "translate during outage: connection refused (fails loudly)"

CODE=$(curl -s -o /tmp/t04-tts-down.json --max-time 60 -w "%{http_code}" \
  -X POST "${SPEECH_URL}/v3/text-to-speech" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d "$(python3 - "$TRANSLATED" "$VOICEPRINT_PATH" <<'EOF'
import json, sys
print(json.dumps({"input": sys.argv[1], "reference_voiceprint_path": sys.argv[2]}))
EOF
)")
echo "tts during outage: HTTP ${CODE} $(head -c 80 /tmp/t04-tts-down.json 2>/dev/null)"
test "${CODE}" != "200" \
  && echo "checkpoint 5a passed: one killed service broke two pipelines — Linga is a shared dependency"

source /tmp/inaya_env.sh
export INAYA_LABS_ENVIRONMENT=local
nohup /Users/test/projects/Software/InayaLabs/target/debug/linga-service > /tmp/linga-service.log 2>&1 &
sleep 3

ES2=$(curl -sf -m 180 -X POST "${LINGA_URL}/v3/translation/translate" \
  -H "Authorization: Bearer ${TOKEN}" "${KEYS[@]}" \
  -H "Content-Type: application/json" \
  -d '{"source":{"locale":"en-US"},"target":{"locale":"ar-SA"},"text":"Water the tomatoes twice a week."}')
python3 -c 'import json,sys
d = json.load(sys.stdin)
assert d["translated_text"], d
print("checkpoint 5b passed: translator restarted — Arabic translation flowing again")' <<< "${ES2}"