VoiceKit — Python SDK

Official Python wrapper for VoiceKit: neural speech synthesis, transcription, sentiment analysis, and batch operations.

Install

pip install voicekit-client

Quick start

from voicekit import VoiceKitClient, b64

client = VoiceKitClient(api_key="YOUR_KEY")

# Synthesis → raw audio bytes
audio = client.synthesize("Привет! Это синтез русской речи.", voice="preset_anna", format="mp3")
with open("speech.mp3", "wb") as f:
    f.write(audio)

# Streaming (Pro/Business)
for chunk in client.synthesize_stream("Первое предложение. Второе."):
    pass  # write chunks to a file or socket

# Transcription (async → poll)
job = client.transcribe("audio.wav", keyterms=["диагноз"])
result = client.get_transcription_job(job["job_id"])
while result["status"] not in ("completed", "failed"):
    result = client.get_transcription_job(job["job_id"])

# Short-file sync transcription
transcript = client.transcribe_sync("audio.wav")

# Analysis (sentiment + keywords + entities)
analysis = client.analyze_sync("audio.wav")

# Text intelligence
lang = client.detect_language("Как дела?")
topics = client.topics("Нейросети и алгоритмы")
summary = client.summarize("Длинный текст для резюме.", max_sentences=3)
moderation = client.moderate("Это оскорбительное сообщение.")

# Batches
batch = client.batch_synthesize([
    {"text": "Первый текст", "voice": "preset_anna"},
    {"text": "Второй текст", "voice": "dmitri"},
])
status = client.get_batch(batch["batch_id"])

analysis_batch = client.batch_analyze([
    {"audio": b64("a.wav"), "language": "ru"},
    {"audio": b64("b.wav"), "language": "ru"},
])

# Voice cloning (Pro/Business)
clone = client.create_clone_voice(
    name="My voice",
    prompt_text="Точный текст образца.",
    samples="reference.wav",
)
print(client.list_clone_voices())
client.delete_clone_voice(clone["id"])

# VAD (speech segments)
segments = client.vad("audio.wav")

# Account
usage = client.usage()
balance = client.billing_balance()

Audio effects (Pro/Business)

# Inline during synthesis — the chain is applied to the synthesized audio
audio = client.synthesize(
    "Привет!",
    effects='[{"type":"reverb","room_size":0.5},{"type":"pitch","semitones":2}]',
)

# Async processing of an existing file
import time

job = client.apply_audio_effects("voice.mp3", [{"type": "compressor", "ratio": 3}])
while client.get_audio_effects_job(job["job_id"])["status"] not in ("completed", "failed"):
    time.sleep(1)
result = client.download_audio_effects(job["job_id"])
open("voice_fx.mp3", "wb").write(result)

WebSocket streaming (Pro/Business)

Требует опциональной зависимости:

pip install "voicekit-client[streaming]"

import asyncio

async def main():
    client = VoiceKitClient(api_key="YOUR_KEY")

    stream = await client.transcribe_stream(language="ru", keyterms=["диагноз"])
    await stream.send_audio(pcm16_chunk_1)   # raw PCM16, 16 kHz mono
    await stream.send_audio(pcm16_chunk_2)
    await stream.stop()                       # finalize the utterance
    async for event in stream:                # session / vad / partial / final / error
        print(event["type"], event)
    await stream.close()

    vad = await client.vad_stream()           # VAD events only (speech_started/ended)
    await vad.send_audio(pcm16_chunk)
    await vad.stop()
    async for event in vad:
        print(event["type"], event)
    await vad.close()

asyncio.run(main())

Configuration

Errors raise VoiceKitError with .status (HTTP status), .code (machine-readable code) and .message.