Audio and speech

# Audio in, text out. -w0 keeps the base64 on one line (GNU coreutils;
# on macOS use: base64 -i question.wav).
AUDIO=$(base64 -w0 question.wav)
curl https://api.liquid.ai/openai/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<EOF
{
  "model": "lfm3-audio-2b",
  "messages": [
    {"role": "system", "content": "Perform ASR in English."},
    {"role": "user", "content": [
      {"type": "input_audio", "input_audio": {"data": "$AUDIO", "format": "wav"}}
    ]}
  ]
}
EOF

import base64
import os
import wave

from openai import OpenAI

client = OpenAI(api_key=os.environ["LIQUID_API_KEY"], base_url="https://api.liquid.ai/openai/v1")

with open("question.wav", "rb") as f:
    question = base64.b64encode(f.read()).decode()

stream = client.chat.completions.create(
    model="lfm3-audio-2b",
    modalities=["text", "audio"],
    # The OpenAI SDK requires a voice; any value works and the model's default
    # voice speaks. Pick a voice in the system prompt instead.
    audio={"voice": "alloy", "format": "pcm16"},
    stream=True,
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "input_audio", "input_audio": {"data": question, "format": "wav"}}
            ],
        }
    ],
)

transcript, pcm = "", bytearray()
for chunk in stream:
    if not chunk.choices:
        continue
    audio = chunk.choices[0].delta.model_dump().get("audio") or {}
    transcript += audio.get("transcript") or ""
    if audio.get("data"):
        # 16-bit PCM, 24 kHz, mono: play it as it arrives, or keep it as here.
        pcm += base64.b64decode(audio["data"])

with wave.open("reply.wav", "wb") as out:
    out.setnchannels(1)
    out.setsampwidth(2)
    out.setframerate(24_000)
    out.writeframes(bytes(pcm))
print(transcript)