Audio: TTS and STT

audio = client.audio.speech.create(
    model="tts-1",
    voice="nova",
    input="Welcome to Infery. Your audio is being generated now.",
    response_format="mp3",
    speed=1.0,
)
audio.stream_to_file("welcome.mp3")

with client.audio.speech.with_streaming_response.create(
    model="tts-1",
    voice="nova",
    input=long_text,
) as resp:
    for chunk in resp.iter_bytes(8192):
        write_to_pipe(chunk)

tr = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("meeting.mp3", "rb"),
    response_format="verbose_json",
    language="en",
)
print(tr.text)
for s in tr.segments:
    print(f"[{s.start:.1f}s] {s.text}")

import subprocess, tempfile, os

def split(input_path: str, segment_seconds: int = 600) -> list[str]:
    out_dir = tempfile.mkdtemp()
    pattern = os.path.join(out_dir, "part_%03d.mp3")
    subprocess.run([
        "ffmpeg", "-i", input_path,
        "-f", "segment", "-segment_time", str(segment_seconds),
        "-c:a", "libmp3lame", "-b:a", "64k",
        pattern,
    ], check=True)
    return sorted(os.path.join(out_dir, f) for f in os.listdir(out_dir))

def transcribe_long(path: str) -> str:
    parts = split(path)
    return "\n".join(
        client.audio.transcriptions.create(
            model="whisper-1",
            file=open(p, "rb"),
            response_format="text",
        )
        for p in parts
    )

vtt = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("video.mp4", "rb"),
    response_format="vtt",
)
open("subs.vtt", "w").write(vtt)  # ready for HTML5 <track>

tr = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("call.wav", "rb"),
    response_format="verbose_json",
    timestamp_granularities=["word"],
)
for w in tr.words:
    print(w.word, w.start, w.end)

def respond(user_audio_path: str) -> bytes:
    user_text = client.audio.transcriptions.create(
        model="whisper-1",
        file=open(user_audio_path, "rb"),
    ).text

    reply = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": user_text}],
    ).choices[0].message.content

    speech = client.audio.speech.create(
        model="tts-1",
        voice="nova",
        input=reply,
        response_format="opus",
    )
    return speech.read()