Voice agents for language learning and conversation practice

Voice Agent API — Spanish conversation tutor with native-accent voice

# Voice Agent API: Spanish conversation tutor with native-accent voice
import asyncio, json, websockets

API_KEY = "YOUR_API_KEY"

async def run_tutor():
    async with websockets.connect(
        "wss://agents.assemblyai.com/v1/ws",
        additional_headers={"Authorization": f"Bearer {API_KEY}"},
    ) as ws:
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "system_prompt": (
                    "You are a friendly B1-intermediate Spanish tutor. "
                    "Speak Spanish, keep replies under 2 sentences, and ask "
                    "follow-up questions. When the learner mispronounces a "
                    "word, call pronunciation_feedback with the word and a "
                    "short tip — do not correct out loud."
                ),
                "greeting": "¡Hola! Cuéntame sobre tu fin de semana. ¿Qué hiciste?",
                "input": {"keyterms": ["mercado", "frutas", "fin de semana", "compré"]},
                "output": {"voice": "lucia"},  # Spanish native-accent voice
                "tools": [{
                    "type": "function",
                    "name": "pronunciation_feedback",
                    "description": "Send a pronunciation tip to the learner UI.",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "word": {"type": "string"},
                            "tip": {"type": "string"},
                        },
                        "required": ["word", "tip"],
                    },
                }],
            },
        }))
        async for msg in ws:
            handle(json.loads(msg))  # transcript.user, reply.audio, tool.call, ...

Universal-3.5 Pro Realtime — word-level pronunciation scoring

# Universal-3.5 Pro Realtime: word-level pronunciation scoring
import asyncio, json, websockets
from urllib.parse import urlencode

API_KEY = "YOUR_API_KEY"

params = urlencode({
    "sample_rate": 16000,
    "speech_model": "u3-rt-pro",
    "language_detection": "true",              # tag each turn with detected language
    "keyterms_prompt": json.dumps([
        "mercado", "frutas", "fin de semana",
        "ayer", "compré", "ir al",
    ]),
    "format_turns": "true",
})

CONFIDENCE_THRESHOLD = 0.70                    # tune per learner level

async def score_pronunciation(audio_iter, send_to_learner_ui):
    url = f"wss://streaming.assemblyai.com/v3/ws?{params}"
    async with websockets.connect(
        url, additional_headers={"Authorization": API_KEY},
    ) as ws:
        async def send_audio():
            async for chunk in audio_iter:
                await ws.send(chunk)
        asyncio.create_task(send_audio())
        async for raw in ws:
            evt = json.loads(raw)
            if evt.get("type") == "Turn" and evt.get("end_of_turn"):
                words = evt.get("words", [])
                low_conf = [
                    w for w in words
                    if w.get("confidence", 1.0) < CONFIDENCE_THRESHOLD
                ]
                send_to_learner_ui({
                    "transcript": evt["transcript"],
                    "needs_practice": [{"word": w["text"], "score": w["confidence"]}
                                       for w in low_conf],
                })