Python SDK

pip install soniox

export SONIOX_API_KEY=<YOUR_API_KEY>

from soniox import SonioxClient
from soniox.types import RealtimeSTTConfig, Token
from soniox.utils import render_tokens, throttle_audio, start_audio_thread

# Grab the demo file from: 
# https://github.com/soniox/soniox_examples/raw/refs/heads/master/speech_to_text/assets/coffee_shop.mp3
AUDIO_FILE = "coffee_shop.mp3"

client = SonioxClient()
config = RealtimeSTTConfig(model="stt-rt-v4", audio_format="mp3")
final_tokens: list[Token] = []
non_final_tokens: list[Token] = []

def realtime():
    # Create new real-time websocket session
    with client.realtime.stt.connect(config=config) as session:

        # Stream audio to websocket
        start_audio_thread(session, throttle_audio(AUDIO_FILE, delay_seconds=0.1))

        # Receive events from Soniox Real-time STT
        for event in session.receive_events():
            for token in event.tokens:
                if token.is_final:
                    final_tokens.append(token)
                else:
                    non_final_tokens.append(token)
            print(render_tokens(final_tokens, non_final_tokens))
            non_final_tokens.clear()

realtime()

from soniox import SonioxClient

client = SonioxClient()

# Create new transcription from `audio_url`
transcription = client.stt.transcribe(
    audio_url="https://soniox.com/media/examples/coffee_shop.mp3",
)

# Wait until transcription processing is finished
client.stt.wait(transcription.id)

# Get transcription transcript and print it
transcript = client.stt.get_transcript(transcription.id)
print(transcript.text)

from soniox import SonioxClient

client = SonioxClient()

written = client.tts.generate_to_file(
    "hello.wav",
    text="Hello from Soniox Python SDK text-to-speech.",
    model="tts-rt-v1-preview",
    language="en",
    voice="Adrian",
    audio_format="wav",
)
print(f"Wrote {written} bytes")

from uuid import uuid4
from soniox import SonioxClient
from soniox.types import RealtimeTTSConfig

client = SonioxClient()
config = RealtimeTTSConfig(
    stream_id=f"tts-{uuid4()}",
    model="tts-rt-v1-preview",
    language="en",
    voice="Adrian",
    audio_format="wav",
)

audio_chunks: list[bytes] = []
with client.realtime.tts.connect(config=config) as session:
    session.send_text_chunks(["Hello from Soniox real-time TTS."], terminate=True)
    for chunk in session.receive_audio_chunks():
        audio_chunks.append(chunk)

with open("hello-realtime.wav", "wb") as f:
    f.write(b"".join(audio_chunks))