convozen 0.3.4

Python SDK for ConvoZen TTS and STT services

ConvoZen Voice SDK

Text-to-Speech (TTS) and Speech-to-Text (STT) for Python.

One API key for both TTS and STT.

Install

pip install convozen

Requires Python 3.9+

---

TTS — Convert Text to Speech

Copy and run:

import convozen

client = convozen.Client(api_key="your-api-key")

audio = client.tts.synthesize("नमस्ते… मुझे आपके सर्विस के बारे में थोड़ी जानकारी चाहिए।", language="hi")

with open("output.wav", "wb") as f:
    f.write(audio)

With options:

import convozen

client = convozen.Client(api_key="your-api-key")

audio = client.tts.synthesize(
    text="Welcome to Playground.",
    language="en",          # default: "en"
    voice="roohi",          # default: "roohi"
    model="ragini-v1",      # default: "ragini-v1"
    speed=1.2,              # default: 1.0
)

with open("output.wav", "wb") as f:
    f.write(audio)

Parameters

Parameter	Type	Default	Description
text	str	required	Text to convert to speech
language	str	"en"	Language code (see supported languages below)
voice	str	"roohi"	Voice ID for synthesis (see available voices below)
model	str	"ragini-v1"	TTS model to use. Currently only ragini-v1 is available
speed	float	1.0	Speech speed. 0.5 = half speed, 2.0 = double speed
stream	bool	False	If True, returns audio chunks as they are generated
format	str	"wav"	Audio output format. Currently only wav is supported

Streaming

import convozen

client = convozen.Client(api_key="your-api-key")

for chunk in client.tts.synthesize("Long text here...", language="en", stream=True):
    audio_player.write(chunk)

Available Voices

Voice	ID	Default
Roohi	roohi	Yes
Amaya	amaya
Kiyansh	kiyansh
Neeraj	neeraj
Manya	manya
Nidhi	nidhi
Ira	ira
Trisha	trisha
Charvi	charvi

audio = client.tts.synthesize("Hello", language="en", voice="roohi")

---

STT — Convert Speech to Text

Copy and run:

import convozen

client = convozen.Client(api_key="your-api-key")

result = client.stt.transcribe("recording.wav")
print(result.text)    # "hello how can I help you"
print(result.score)   # -2.45 (confidence — closer to 0 is better)

Specify Languages

If you know which languages are spoken in the audio, pass them in lang_tags. This improves accuracy — especially for multilingual audio like Hindi + English call recordings:

result = client.stt.transcribe(
    "recording.wav",
    lang_tags=["hi", "en"],
)
print(result.text)  # "हां मुझे appointment reschedule करना है"

Keyword Boosting

Have domain-specific words that the model keeps getting wrong? Pass them in keywords and the model will try harder to recognize them:

# Without keyword boosting: "can you tell me about conversion"
# With keyword boosting:    "can you tell me about convozen"

result = client.stt.transcribe(
    "recording.wav",
    keywords=["convozen", "akshara"],
)

Parameters

Parameter	Type	Default	Description
audio	str	required	Path to the audio file
lang_tags	list[str]	None	Languages in the audio ("en", "hi", "te", etc.)
keywords	list[str]	None	Words the model should try harder to recognize

---

Supported Languages

Code	Language	TTS	STT
en	English	Yes	Yes
hi	Hindi	Yes	Yes
ta	Tamil	Yes	Yes
te	Telugu	Yes	Yes
kn	Kannada	Yes	Yes
mr	Marathi	—	Yes
bn	Bengali	—	Yes
gu	Gujarati	—	Yes
ml	Malayalam	—	Yes

---

Check Credits

import convozen

client = convozen.Client(api_key="your-api-key")
info = client.account.info()
print(info.credits.tts.balance)
print(info.credits.stt.balance)

---

Error Handling

import convozen
from convozen import AuthenticationError, RateLimitError, APIError

client = convozen.Client(api_key="your-api-key")

try:
    audio = client.tts.synthesize("Hello")
except AuthenticationError:
    print("Invalid API key")
except RateLimitError:
    print("Too many requests")
except APIError as e:
    print(f"Server error: {e}")

---

Standalone Clients

from convozen import TTS, STT

tts = TTS(api_key="your-api-key")
audio = tts.synthesize("Hello", language="hi")

stt = STT(api_key="your-api-key")
result = stt.transcribe(
        audio_path,
        type="transcript"
    )

print("=== Transcript ===")
print(result.text)

# =========================================================
# Speaker Diarization (default behavior)
# =========================================================
result = client.stt.transcribe(audio_path)

print("\n=== Speaker Turns ===")
for turn in result.turns:
    print(f"[{turn.speaker_id}] {turn.start_sec:.2f}s - {turn.end_sec:.2f}s : {turn.transcript}")