gl-speech 0.0.1b9__tar.gz

gl_speech-0.0.1b9/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 GDP Labs
+
+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.

gl_speech-0.0.1b9/MANIFEST.in

@@ -0,0 +1,5 @@
+global-exclude *.key
+global-exclude *.env
+global-exclude *.aes
+prune tests
+prune build

gl_speech-0.0.1b9/PKG-INFO

@@ -0,0 +1,370 @@
+Metadata-Version: 2.4
+Name: gl-speech
+Version: 0.0.1b9
+Summary: GL Speech Python Client - Language binding SDK for Prosa Speech API
+Author-email: GDP Labs <jobs@gdplabs.id>
+Requires-Python: <3.13,>=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: pydantic>=2.0.0
+Dynamic: license-file
+
+# GL Speech SDK
+
+A Python SDK for interacting with the GL Speech API, providing speech-to-text (STT), text-to-speech (TTS), and webhook management capabilities.
+
+## Prerequisites
+
+- **Python** ≥3.11,<3.13 (3.11 or 3.12)
+
+## Installation
+
+```bash
+pip install gl-speech
+```
+
+Or with uv:
+
+```bash
+uv add gl-speech
+```
+
+## Quick Start
+
+STT and TTS use different API keys and base URLs. Create two clients. Webhooks for STT jobs use the STT client; webhooks for TTS jobs use the TTS client.
+
+```python
+from gl_speech_sdk import SpeechClient
+
+stt_client = SpeechClient(api_key="your-stt-api-key", base_url="https://api.prosa.ai/v2/speech/")
+tts_client = SpeechClient(api_key="your-tts-api-key", base_url="https://api.prosa.ai/v2/speech/")
+
+# Speech-to-Text
+result = stt_client.stt.transcribe(
+    data="<base64-encoded-audio>",
+    model="stt-general",
+    wait=True
+)
+print(result.result)
+
+# Text-to-Speech
+result = tts_client.tts.synthesize(
+    text="Hello, world!",
+    model="tts-dimas-formal",
+    wait=True
+)
+print(result.result)
+
+# Webhooks: STT job events use STT client, TTS job events use TTS client
+stt_endpoint = stt_client.webhooks.create_endpoint(
+    url="https://your-server.com/webhook-stt",
+    event_filters=["stt.job.completed"]
+)
+tts_endpoint = tts_client.webhooks.create_endpoint(
+    url="https://your-server.com/webhook-tts",
+    event_filters=["tts.job.completed"]
+)
+```
+
+## Configuration
+
+### Environment Variables
+
+Set separate credentials for STT and TTS:
+
+- `GLSPEECH_STT_API_KEY`: API key for Speech-to-Text
+- `GLSPEECH_STT_BASE_URL`: Base URL for STT (default: `https://api.prosa.ai/v2/speech/`)
+- `GLSPEECH_TTS_API_KEY`: API key for Text-to-Speech
+- `GLSPEECH_TTS_BASE_URL`: Base URL for TTS (default: `https://api.prosa.ai/v2/speech/`)
+
+Webhook management is per job type: use the STT client for STT job webhooks, the TTS client for TTS job webhooks.
+
+### Client Initialization
+
+```python
+from gl_speech_sdk import SpeechClient
+
+# Two clients (STT and TTS have different keys)
+stt_client = SpeechClient(
+    api_key="your-stt-api-key",
+    base_url="https://api.prosa.ai/v2/speech/",
+    timeout=60.0,
+    default_headers={"X-Custom-Header": "value"}
+)
+tts_client = SpeechClient(
+    api_key="your-tts-api-key",
+    base_url="https://api.prosa.ai/v2/speech/",
+    timeout=60.0,
+    default_headers={"X-Custom-Header": "value"}
+)
+
+# Or from environment variables
+import os
+os.environ["GLSPEECH_STT_API_KEY"] = "your-stt-api-key"
+os.environ["GLSPEECH_STT_BASE_URL"] = "https://api.prosa.ai/v2/speech/"
+os.environ["GLSPEECH_TTS_API_KEY"] = "your-tts-api-key"
+os.environ["GLSPEECH_TTS_BASE_URL"] = "https://api.prosa.ai/v2/speech/"
+stt_client = SpeechClient(api_key=os.getenv("GLSPEECH_STT_API_KEY"), base_url=os.getenv("GLSPEECH_STT_BASE_URL"))
+tts_client = SpeechClient(api_key=os.getenv("GLSPEECH_TTS_API_KEY"), base_url=os.getenv("GLSPEECH_TTS_BASE_URL"))
+```
+
+## Speech-to-Text (STT)
+
+Use `stt_client` for all STT operations.
+
+### List Available Models
+
+```python
+models = stt_client.stt.list_models()
+for model in models:
+    print(f"{model['name']}: {model['label']}")
+```
+
+### Transcribe Audio
+
+```python
+# Synchronous (wait for result)
+result = stt_client.stt.transcribe(
+    model="stt-general",
+    wait=True,
+    data="<base64-encoded-audio>",
+    label="My audio file"
+)
+print(result.result)
+
+# Asynchronous (get job_id, poll later)
+result = stt_client.stt.transcribe(
+    model="stt-general",
+    wait=False,
+    uri="https://example.com/audio.wav"
+)
+job_id = result.job_id
+
+# Check status
+status = stt_client.stt.get_status(job_id)
+print(f"Status: {status.status}, Progress: {status.progress}")
+
+# Get result when complete
+result = stt_client.stt.get_job(job_id)
+print(result.result)
+```
+
+### Advanced Configuration
+
+```python
+result = stt_client.stt.transcribe(
+    model="stt-general",
+    wait=True,
+    data="<base64-encoded-audio>",
+    speaker_count=2,           # Expected number of speakers
+    include_filler=True,       # Include filler words
+    auto_punctuation=True,     # Auto-add punctuation
+    enable_spoken_numerals=True,  # Convert "one" to "1"
+    enable_speech_insights=True,  # Speech analytics
+    enable_voice_insights=True,   # Voice analytics
+)
+```
+
+### List and Manage Jobs
+
+```python
+# List jobs with filters
+jobs = stt_client.stt.list_jobs(
+    page=1,
+    per_page=10,
+    from_date="2024-01-01",
+    until_date="2024-01-31",
+    query_text="hello"
+)
+
+# Archive a job
+stt_client.stt.archive(job_id)
+```
+
+## Text-to-Speech (TTS)
+
+Use `tts_client` for all TTS operations.
+
+### List Available Models
+
+```python
+models = tts_client.tts.list_models()
+for model in models:
+    print(f"{model['name']}: {model['voice']} ({model['gender']})")
+```
+
+### Synthesize Speech
+
+```python
+# Synchronous (wait for result)
+result = tts_client.tts.synthesize(
+    text="Hello, world!",
+    model="tts-dimas-formal",
+    wait=True
+)
+audio_data = result.result["data"]  # Base64-encoded audio
+
+# Get as signed URL instead
+result = tts_client.tts.synthesize(
+    text="Hello, world!",
+    model="tts-dimas-formal",
+    wait=True,
+    as_signed_url=True
+)
+audio_url = result.result["path"]
+
+# Asynchronous
+result = tts_client.tts.synthesize(
+    text="Long text content...",
+    model="tts-dimas-formal",
+    wait=False
+)
+job_id = result.job_id
+
+# Poll for completion
+result = tts_client.tts.get_job(job_id, as_signed_url=True)
+```
+
+### Advanced Configuration
+
+```python
+result = tts_client.tts.synthesize(
+    text="Hello, world!",
+    model="tts-dimas-formal",
+    wait=True,
+    pitch=0.5,           # Pitch adjustment (-1.0 to 1.0)
+    tempo=1.2,           # Speed adjustment (0.5 to 2.0)
+    audio_format="mp3",  # "opus", "mp3", or "wav"
+    label="My synthesis"
+)
+```
+
+### List and Manage Jobs
+
+```python
+# List jobs
+jobs = tts_client.tts.list_jobs(page=1, per_page=10)
+
+# Count jobs
+count = tts_client.tts.count_jobs(from_date="2024-01-01")
+
+# Get job status
+status = tts_client.tts.get_status(job_id)
+
+# Archive a job
+tts_client.tts.archive(job_id)
+```
+
+## Webhook Management
+
+### Webhooks and API keys
+
+Webhook **management** is split by job type:
+
+- **STT job webhooks** (e.g. `stt.job.completed`) use the **STT** API key and base URL → use `stt_client.webhooks`.
+- **TTS job webhooks** (e.g. `tts.job.completed`) use the **TTS** API key and base URL → use `tts_client.webhooks`.
+
+Create and manage endpoints on the client that matches the events you want to receive.
+
+### Create a Webhook Endpoint
+
+```python
+# Endpoint for STT job events (uses STT key)
+stt_endpoint = stt_client.webhooks.create_endpoint(
+    url="https://your-server.com/webhook-stt",
+    event_filters=["stt.job.completed"],
+    ssl_verification=True
+)
+
+# Endpoint for TTS job events (uses TTS key)
+tts_endpoint = tts_client.webhooks.create_endpoint(
+    url="https://your-server.com/webhook-tts",
+    event_filters=["tts.job.completed"],
+    ssl_verification=True
+)
+print(f"STT Endpoint ID: {stt_endpoint.id}, Secret: {stt_endpoint.secrets[0].key}")
+print(f"TTS Endpoint ID: {tts_endpoint.id}, Secret: {tts_endpoint.secrets[0].key}")
+```
+
+### List Endpoints
+
+```python
+# List STT webhook endpoints
+stt_endpoints = stt_client.webhooks.list_endpoints()
+
+# List TTS webhook endpoints
+tts_endpoints = tts_client.webhooks.list_endpoints()
+for ep in tts_endpoints:
+    print(f"{ep.id}: {ep.url}")
+```
+
+### Update and Delete Endpoints
+
+```python
+# Update/delete on the same client you used to create (STT or TTS)
+stt_client.webhooks.update_endpoint(
+    endpoint_id="endpoint-123",
+    url="https://your-server.com/new-webhook",
+    event_filters=[]
+)
+stt_client.webhooks.delete_endpoint("endpoint-123")
+```
+
+### Rotate Secrets
+
+```python
+tts_client.webhooks.rotate_secret(
+    endpoint_id="endpoint-123",
+    days=3,  # Old secret valid for 3 days
+    hours=0
+)
+```
+
+### Event Management
+
+```python
+# List events (from the client whose webhooks you're querying)
+events = tts_client.webhooks.list_events(
+    from_date="2024-01-01",
+    to_date="2024-01-31"
+)
+event = tts_client.webhooks.get_event("event-123")
+print(event.data)
+```
+
+### Delivery Management
+
+```python
+deliveries = tts_client.webhooks.list_deliveries("endpoint-123")
+ticket = tts_client.webhooks.replay_delivery("delivery-123")
+tickets = tts_client.webhooks.replay_failed_deliveries("endpoint-123")
+ticket = tts_client.webhooks.test_endpoint("endpoint-123")
+```
+
+## Error Handling
+
+```python
+import httpx
+from gl_speech_sdk import SpeechClient
+
+stt_client = SpeechClient(api_key="your-stt-api-key", base_url="https://api.prosa.ai/v2/speech/")
+
+try:
+    result = stt_client.stt.transcribe(model="stt-general", data="invalid")
+except httpx.HTTPStatusError as e:
+    print(f"HTTP Error: {e.response.status_code}")
+    print(f"Response: {e.response.text}")
+except ValueError as e:
+    print(f"Validation Error: {e}")
+```
+
+## API Reference
+
+- [STT API Documentation](https://gdplabs.gitbook.io/gl-speech/api-contract/speech-to-text-stt)
+- [TTS API Documentation](https://gdplabs.gitbook.io/gl-speech/api-contract/text-to-speech-tts)
+- [Webhook API Documentation](https://gdplabs.gitbook.io/gl-speech/api-contract/webhooks)
+
+## License
+
+MIT License.