Quickstart

curl --fail --show-error https://api.sawtakarabi.ai/v1/voices \
  -H "Authorization: Bearer $SAWTAK_API_KEY"

curl --fail --show-error https://api.sawtakarabi.ai/v1/audio/speech \
  -H "Authorization: Bearer $SAWTAK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": "<VOICE_ID>",
    "input": "مرحباً بك",
    "response_format": "wav"
  }' \
  --dump-header speech.headers \
  --output speech.partial.wav

python3 -m venv .venv
source .venv/bin/activate
python -m pip install 'openai>=1.102.0,<3'
export SAWTAK_VOICE_ID='<VOICE_ID>'

import os
import time
import uuid
import wave
from pathlib import Path
from urllib.parse import quote

from openai import OpenAI

output = Path("speech.wav")
partial = Path("speech.partial.wav")
if output.exists() or partial.exists():
    raise SystemExit("Reuse the existing audio or choose new output filenames.")

with OpenAI(
    api_key=os.environ["SAWTAK_API_KEY"],
    base_url="https://api.sawtakarabi.ai/v1",
    max_retries=0,
    timeout=180.0,
) as client:
    with partial.open("xb") as file, wave.open(file, "wb") as wav:
        wav.setparams((1, 2, 24000, 0, "NONE", "not compressed"))
        received = 0
        pending = b""
        with client.audio.speech.with_streaming_response.create(
            model="arabic-tts-1",
            voice=os.environ["SAWTAK_VOICE_ID"],
            input="مرحباً بك في صوتك عربي.",
            response_format="pcm",
            extra_body={"sample_rate": 24000},
            extra_headers={"Idempotency-Key": str(uuid.uuid4())},
        ) as response:
            operation_id = response.headers.get("x-request-id")
            print("Operation:", operation_id, flush=True)
            if (
                response.headers.get("content-type", "").split(";")[0] != "audio/pcm"
                or response.headers.get("x-sample-rate") != "24000"
                or response.headers.get("x-channels") != "1"
            ):
                raise RuntimeError("Unexpected audio format; inspect the operation.")
            for chunk in response.iter_bytes():
                pending += chunk
                size = len(pending) - len(pending) % 2
                wav.writeframes(pending[:size])
                received += size
                pending = pending[size:]

    if not received or pending or not operation_id:
        raise RuntimeError("Incomplete audio or missing operation ID; keep the partial file.")
    for attempt in range(5):
        operation = client.get(
            "/operations/" + quote(operation_id, safe=""), cast_to=object
        )
        if operation["state"] == "terminal":
            break
        time.sleep(1)
    if operation.get("outcome") != "completed" or operation.get("completion_bytes") != received:
        raise RuntimeError("Completion unconfirmed; keep the partial file and inspect the operation.")

os.link(partial, output)
partial.unlink()
print(f"Saved {output}: {received / (24000 * 2):.2f} seconds")