convozen 0.3.1__tar.gz

convozen-0.3.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Convozen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

convozen-0.3.1/MANIFEST.in

@@ -0,0 +1,6 @@
+recursive-exclude tests *
+exclude *.ipynb
+recursive-exclude dist *
+recursive-exclude build *
+recursive-exclude *.egg-info *
+global-exclude __pycache__ *.py[cod]

convozen-0.3.1/PKG-INFO

@@ -0,0 +1,206 @@
+Metadata-Version: 2.4
+Name: convozen
+Version: 0.3.1
+Summary: Python SDK for ConvoZen TTS and STT services
+Author: Convozen
+License-Expression: MIT
+Keywords: tts,stt,speech,voice,convozen
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests<3.0,>=2.28.0
+Provides-Extra: async
+Requires-Dist: httpx<1.0,>=0.24.0; extra == "async"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: responses; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: anyio[trio]; extra == "dev"
+Requires-Dist: respx; extra == "dev"
+Requires-Dist: httpx<1.0,>=0.24.0; extra == "dev"
+Dynamic: license-file
+
+# ConvoZen Voice SDK
+
+Text-to-Speech (TTS) and Speech-to-Text (STT) for Python.
+
+> One API key for both TTS and STT.
+
+## Install
+
+```bash
+pip install convozen
+```
+
+Requires Python 3.9+
+
+---
+
+## TTS — Convert Text to Speech
+
+Copy and run:
+
+```python
+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:
+
+```python
+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
+
+```python
+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` | |
+
+```python
+audio = client.tts.synthesize("Hello", language="en", voice="roohi")
+```
+
+---
+
+## STT — Convert Speech to Text
+
+Copy and run:
+
+```python
+import convozen
+
+client = convozen.Client(api_key="your-api-key")
+
+text = client.stt.transcribe("recording.wav")
+print(text)
+```
+
+### Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `audio` | `str` | *required* | Path to the audio file (WAV format) |
+| `model` | `str` | `"akshara-v1"` | STT model to use. Currently only `akshara-v1` is available |
+
+---
+
+## 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
+
+```python
+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
+
+```python
+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
+
+```python
+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")
+text = stt.transcribe("audio.wav")
+```

convozen-0.3.1/README.md

@@ -0,0 +1,175 @@
+# ConvoZen Voice SDK
+
+Text-to-Speech (TTS) and Speech-to-Text (STT) for Python.
+
+> One API key for both TTS and STT.
+
+## Install
+
+```bash
+pip install convozen
+```
+
+Requires Python 3.9+
+
+---
+
+## TTS — Convert Text to Speech
+
+Copy and run:
+
+```python
+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:
+
+```python
+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
+
+```python
+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` | |
+
+```python
+audio = client.tts.synthesize("Hello", language="en", voice="roohi")
+```
+
+---
+
+## STT — Convert Speech to Text
+
+Copy and run:
+
+```python
+import convozen
+
+client = convozen.Client(api_key="your-api-key")
+
+text = client.stt.transcribe("recording.wav")
+print(text)
+```
+
+### Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `audio` | `str` | *required* | Path to the audio file (WAV format) |
+| `model` | `str` | `"akshara-v1"` | STT model to use. Currently only `akshara-v1` is available |
+
+---
+
+## 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
+
+```python
+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
+
+```python
+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
+
+```python
+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")
+text = stt.transcribe("audio.wav")
+```

convozen-0.3.1/convozen/__init__.py

@@ -0,0 +1,45 @@
+__version__ = "0.3.1"
+
+from .client import Client, STT, TTS
+
+from convozen._internal.exceptions import (
+    ConvozenError,
+    AuthenticationError,
+    RateLimitError,
+    APIError,
+)
+from convozen._internal.enums import Language, AudioFormat, VoiceId
+from convozen._internal.types import (
+    TTSResponse,
+    STTResponse,
+    CreditBalance,
+    Credits,
+    AccountInfo,
+    RateLimitInfo,
+    UsageSummary,
+    UsageByDay,
+)
+
+__all__ = [
+    "Client",
+    "STT",
+    "TTS",
+    # Enums
+    "Language",
+    "AudioFormat",
+    "VoiceId",
+    # Types
+    "TTSResponse",
+    "STTResponse",
+    "CreditBalance",
+    "Credits",
+    "AccountInfo",
+    "RateLimitInfo",
+    "UsageSummary",
+    "UsageByDay",
+    # Errors
+    "ConvozenError",
+    "AuthenticationError",
+    "RateLimitError",
+    "APIError",
+]

convozen-0.3.1/convozen/_internal/account.py

@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from typing import List
+
+from .config import Config
+from .transport.http import HTTPClient
+from .transport.async_http import AsyncHTTPClient
+from .types import AccountInfo, CreditBalance, Credits, RateLimitInfo, UsageSummary, UsageByDay
+
+
+class AccountClient:
+    """
+    HTTP client for account- and usage-related endpoints.
+
+    Expects the API gateway to expose:
+      - GET /v1/account
+      - GET /v1/usage?start_date=YYYY-MM-DD&end_date=YYYY-MM-DD
+    """
+
+    def __init__(self, config: Config) -> None:
+        self._config = config
+        self._http = HTTPClient(config)
+        self._async_http = AsyncHTTPClient(config)
+
+    # ---- Synchronous API -------------------------------------------------
+
+    def info(self) -> AccountInfo:
+        response = self._http.get("/v1/account")
+        payload = response.json()
+
+        creds = payload.get("credits") or {}
+        tts_creds = creds.get("tts") or {}
+        stt_creds = creds.get("stt") or {}
+        credits = Credits(
+            tts=CreditBalance(balance=tts_creds.get("balance", 0)),
+            stt=CreditBalance(balance=stt_creds.get("balance", 0)),
+        )
+
+        rate = payload.get("rate_limit") or {}
+        rate_limit = RateLimitInfo(
+            requests_per_minute=rate.get("requests_per_minute", 0),
+            requests_per_day=rate.get("requests_per_day", 0),
+        )
+
+        return AccountInfo(
+            account_id=payload.get("account_id", ""),
+            plan=payload.get("plan", ""),
+            credits=credits,
+            rate_limit=rate_limit,
+        )
+
+    def usage(self, start_date: str, end_date: str) -> UsageSummary:
+        response = self._http.get(
+            "/v1/usage",
+            params={"start_date": start_date, "end_date": end_date},
+        )
+        payload = response.json()
+
+        by_day_payload = payload.get("by_day") or []
+        by_day: List[UsageByDay] = [
+            UsageByDay(date=item.get("date", ""), credits=item.get("credits", 0))
+            for item in by_day_payload
+        ]
+
+        return UsageSummary(
+            total_credits_used=payload.get("total_credits_used", 0),
+            by_model=payload.get("by_model", {}),
+            by_day=by_day,
+        )
+
+    # ---- Async API -------------------------------------------------------
+
+    async def ainfo(self) -> AccountInfo:
+        response = await self._async_http.get("/v1/account")
+        payload = response.json()
+
+        creds = payload.get("credits") or {}
+        tts_creds = creds.get("tts") or {}
+        stt_creds = creds.get("stt") or {}
+        credits = Credits(
+            tts=CreditBalance(balance=tts_creds.get("balance", 0)),
+            stt=CreditBalance(balance=stt_creds.get("balance", 0)),
+        )
+
+        rate = payload.get("rate_limit") or {}
+        rate_limit = RateLimitInfo(
+            requests_per_minute=rate.get("requests_per_minute", 0),
+            requests_per_day=rate.get("requests_per_day", 0),
+        )
+
+        return AccountInfo(
+            account_id=payload.get("account_id", ""),
+            plan=payload.get("plan", ""),
+            credits=credits,
+            rate_limit=rate_limit,
+        )
+
+    async def ausage(self, start_date: str, end_date: str) -> UsageSummary:
+        response = await self._async_http.get(
+            "/v1/usage",
+            params={"start_date": start_date, "end_date": end_date},
+        )
+        payload = response.json()
+
+        by_day_payload = payload.get("by_day") or []
+        by_day: List[UsageByDay] = [
+            UsageByDay(date=item.get("date", ""), credits=item.get("credits", 0))
+            for item in by_day_payload
+        ]
+
+        return UsageSummary(
+            total_credits_used=payload.get("total_credits_used", 0),
+            by_model=payload.get("by_model", {}),
+            by_day=by_day,
+        )

convozen-0.3.1/convozen/_internal/akshara_stt/__init__.py

@@ -0,0 +1 @@
+from .client import STT

convozen-0.3.1/convozen/_internal/akshara_stt/client.py

@@ -0,0 +1,52 @@
+import logging
+
+from ..transport.http import HTTPClient
+from ..transport.async_http import AsyncHTTPClient
+from ..config import Config
+
+logger = logging.getLogger(__name__)
+
+
+class STT:
+
+    def __init__(self, config: Config) -> None:
+        self.http = HTTPClient(config)
+        self.async_http = AsyncHTTPClient(config)
+
+    def transcribe(
+        self,
+        audio: str,
+        model: str = "akshara-v1",
+    ) -> str:
+        logger.debug("STT request: audio=%s model=%s", audio, model)
+
+        with open(audio, "rb") as f:
+            response = self.http.post(
+                "/v1/akshara/transcribe",
+                files={"file": f},
+                data={"model": model},
+            )
+
+        text: str = response.json()["text"]
+        logger.debug("STT response: text_length=%d", len(text))
+        return text
+
+    async def atranscribe(
+        self,
+        audio: str,
+        model: str = "akshara-v1",
+    ) -> str:
+        logger.debug("async STT request: audio=%s model=%s", audio, model)
+
+        with open(audio, "rb") as f:
+            audio_bytes = f.read()
+
+        response = await self.async_http.post(
+            "/v1/akshara/transcribe",
+            files={"file": ("audio", audio_bytes)},
+            data={"model": model},
+        )
+
+        text: str = response.json()["text"]
+        logger.debug("async STT response: text_length=%d", len(text))
+        return text

convozen-0.3.1/convozen/_internal/config.py

@@ -0,0 +1,36 @@
+import os
+from dataclasses import dataclass, field
+from urllib.parse import urlparse
+
+
+@dataclass
+class Config:
+    api_key: str = field(default_factory=lambda: os.environ.get("CONVOZEN_API_KEY", ""))
+    base_url: str = field(
+        default_factory=lambda: os.environ.get("CONVOZEN_BASE_URL", "https://voice.convozen.ai/sdk-models/developer-api/api")
+    )
+    timeout: int = 60
+
+    def __post_init__(self) -> None:
+        if not self.api_key:
+            raise ValueError(
+                "api_key is required. Pass it explicitly or set the "
+                "CONVOZEN_API_KEY environment variable."
+            )
+        if not self.base_url:
+            raise ValueError(
+                "base_url is required. Pass it explicitly or set the "
+                "CONVOZEN_BASE_URL environment variable."
+            )
+
+        parsed = urlparse(self.base_url)
+        if parsed.scheme not in ("http", "https"):
+            raise ValueError(
+                f"base_url must start with http:// or https://, got: {self.base_url}"
+            )
+
+        if self.timeout <= 0:
+            raise ValueError(f"timeout must be positive, got: {self.timeout}")
+
+        # Strip trailing slash for consistent URL joining
+        self.base_url = self.base_url.rstrip("/")