deepctl 0.2.25__tar.gz → 0.2.26__tar.gz

{deepctl-0.2.25/src/deepctl.egg-info → deepctl-0.2.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepctl
-Version: 0.2.25
+Version: 0.2.26
 Summary: Official Deepgram CLI for speech recognition and audio intelligence
 Author-email: Deepgram <devrel@deepgram.com>
 Maintainer-email: Deepgram <devrel@deepgram.com>
@@ -26,7 +26,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click>=8.0.0
-Requires-Dist: deepgram-sdk>=6.0.0rc2
+Requires-Dist: deepgram-sdk>=7.5.0
 Requires-Dist: deepctl-core>=0.1.10
 Requires-Dist: deepctl-cmd-login>=0.1.10
 Requires-Dist: deepctl-cmd-projects>=0.1.10
@@ -255,11 +255,22 @@ cat audio.raw | dg listen --encoding linear16 --sample-rate 16000
 
 Convert text to natural speech. Supports file output and piping.
 
+`aura-*` models use the Speak v1 batch REST API. `flux-*` (Flux TTS) models use
+the Speak v2 WebSocket API and stream by default; their raw `linear16` output is
+wrapped in a WAV container so it is directly playable.
+
 ```bash
+# Aura (v1, batch REST)
 dg speak "Welcome to Deepgram" -o welcome.mp3
 dg speak --file script.txt -o output.mp3 -m aura-2-luna-en
 echo "Hello" | dg speak -o greeting.mp3
-dg speak "Stream me" | ffplay -nodisp -    # pipe to audio player
+dg speak "Stream me" | ffplay -nodisp -            # pipe to audio player
+
+# Flux TTS (v2, WebSocket streaming)
+dg speak "Hello from Flux" -m flux-alexis-en -o hello.wav
+# Piped audio is a streaming WAV; -loglevel error hides ffmpeg's cosmetic
+# end-of-stream notice (the audio is complete).
+dg speak "Hello from Flux" -m flux-alexis-en | ffplay -loglevel error -nodisp -autoexit -
 ```
 
 ### Text Intelligence

{deepctl-0.2.25 → deepctl-0.2.26}/README.md

@@ -173,11 +173,22 @@ cat audio.raw | dg listen --encoding linear16 --sample-rate 16000
 
 Convert text to natural speech. Supports file output and piping.
 
+`aura-*` models use the Speak v1 batch REST API. `flux-*` (Flux TTS) models use
+the Speak v2 WebSocket API and stream by default; their raw `linear16` output is
+wrapped in a WAV container so it is directly playable.
+
 ```bash
+# Aura (v1, batch REST)
 dg speak "Welcome to Deepgram" -o welcome.mp3
 dg speak --file script.txt -o output.mp3 -m aura-2-luna-en
 echo "Hello" | dg speak -o greeting.mp3
-dg speak "Stream me" | ffplay -nodisp -    # pipe to audio player
+dg speak "Stream me" | ffplay -nodisp -            # pipe to audio player
+
+# Flux TTS (v2, WebSocket streaming)
+dg speak "Hello from Flux" -m flux-alexis-en -o hello.wav
+# Piped audio is a streaming WAV; -loglevel error hides ffmpeg's cosmetic
+# end-of-stream notice (the audio is complete).
+dg speak "Hello from Flux" -m flux-alexis-en | ffplay -loglevel error -nodisp -autoexit -
 ```
 
 ### Text Intelligence

{deepctl-0.2.25 → deepctl-0.2.26}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "deepctl"
-version = "0.2.25" # x-release-please-version
+version = "0.2.26" # x-release-please-version
 description = "Official Deepgram CLI for speech recognition and audio intelligence"
 readme = "README.md"
 license = "MIT"
@@ -34,7 +34,7 @@ keywords = [
 requires-python = ">=3.10"
 dependencies = [
     "click>=8.0.0",
-    "deepgram-sdk>=6.0.0rc2",
+    "deepgram-sdk>=7.5.0",
     "deepctl-core>=0.1.10",
     "deepctl-cmd-login>=0.1.10",
     "deepctl-cmd-projects>=0.1.10",
@@ -144,6 +144,11 @@ module = [
 # Optional microphone dependencies (sounddevice, numpy) and the MCP SDK
 # (deepgram_mcp) ship without type stubs.
 ignore_missing_imports = true
+# numpy>=2.2 ships PEP 695 `type` aliases in its stubs, which mypy rejects
+# under python_version = "3.10" (aborting before our code is checked). Skip
+# analyzing these third-party stubs entirely; usages fall back to Any.
+follow_imports = "skip"
+follow_imports_for_stubs = true
 
 [tool.pytest.ini_options]
 testpaths = ["tests", "packages/*/tests"]

{deepctl-0.2.25 → deepctl-0.2.26}/src/deepctl/__init__.py

@@ -1,7 +1,7 @@
 """deepctl - Official command-line interface for Deepgram's speech
 recognition API."""
 
-__version__ = "0.2.25"  # x-release-please-version
+__version__ = "0.2.26"  # x-release-please-version
 __author__ = "Deepgram"
 __email__ = "devrel@deepgram.com"
 __license__ = "MIT"

{deepctl-0.2.25 → deepctl-0.2.26}/src/deepctl/main.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import importlib.metadata
+import os
 import sys
 from contextlib import contextmanager
 from typing import TYPE_CHECKING
@@ -130,6 +131,21 @@ def preprocess_hyphenated_commands(args: list[str]) -> list[str]:
     "-p",
     help="Configuration profile to use",
 )
+@click.option(
+    "--base-url",
+    help=(
+        "Override the API base URL (e.g. https://api.staging.deepgram.com). "
+        "REST and WebSocket endpoints are derived from this host. "
+        "Also settable via the DEEPGRAM_BASE_URL environment variable."
+    ),
+)
+@click.option(
+    "--api-key",
+    help=(
+        "Deepgram API key to use, overriding login/profile/env credentials. "
+        "Intended for testing and CI."
+    ),
+)
 @click.option(
     "--output",
     "-o",
@@ -179,6 +195,8 @@ def cli(
     ctx: click.Context,
     config: str | None,
     profile: str | None,
+    base_url: str | None,
+    api_key: str | None,
     output: str | None,
     quiet: bool,
     verbose: bool,
@@ -206,9 +224,16 @@ def cli(
         enable_timing()
 
     with TimingContext("cli_initialization"):
+        # A --base-url flag overrides the configured/env base URL (flag wins).
+        # Config reads DEEPGRAM_BASE_URL at init, so set it before constructing.
+        if base_url:
+            os.environ["DEEPGRAM_BASE_URL"] = base_url
+
         # Initialize configuration
         ctx.ensure_object(dict)
         ctx.obj["config"] = Config(config_path=config, profile=profile)
+        # Global --api-key passthrough (highest-precedence explicit credential).
+        ctx.obj["api_key"] = api_key
         ctx.obj["timing"] = timing or timing_detailed
         ctx.obj["timing_detailed"] = timing_detailed
 

{deepctl-0.2.25 → deepctl-0.2.26/src/deepctl.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepctl
-Version: 0.2.25
+Version: 0.2.26
 Summary: Official Deepgram CLI for speech recognition and audio intelligence
 Author-email: Deepgram <devrel@deepgram.com>
 Maintainer-email: Deepgram <devrel@deepgram.com>
@@ -26,7 +26,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: click>=8.0.0
-Requires-Dist: deepgram-sdk>=6.0.0rc2
+Requires-Dist: deepgram-sdk>=7.5.0
 Requires-Dist: deepctl-core>=0.1.10
 Requires-Dist: deepctl-cmd-login>=0.1.10
 Requires-Dist: deepctl-cmd-projects>=0.1.10
@@ -255,11 +255,22 @@ cat audio.raw | dg listen --encoding linear16 --sample-rate 16000
 
 Convert text to natural speech. Supports file output and piping.
 
+`aura-*` models use the Speak v1 batch REST API. `flux-*` (Flux TTS) models use
+the Speak v2 WebSocket API and stream by default; their raw `linear16` output is
+wrapped in a WAV container so it is directly playable.
+
 ```bash
+# Aura (v1, batch REST)
 dg speak "Welcome to Deepgram" -o welcome.mp3
 dg speak --file script.txt -o output.mp3 -m aura-2-luna-en
 echo "Hello" | dg speak -o greeting.mp3
-dg speak "Stream me" | ffplay -nodisp -    # pipe to audio player
+dg speak "Stream me" | ffplay -nodisp -            # pipe to audio player
+
+# Flux TTS (v2, WebSocket streaming)
+dg speak "Hello from Flux" -m flux-alexis-en -o hello.wav
+# Piped audio is a streaming WAV; -loglevel error hides ffmpeg's cosmetic
+# end-of-stream notice (the audio is complete).
+dg speak "Hello from Flux" -m flux-alexis-en | ffplay -loglevel error -nodisp -autoexit -
 ```
 
 ### Text Intelligence

{deepctl-0.2.25 → deepctl-0.2.26}/src/deepctl.egg-info/requires.txt

@@ -1,5 +1,5 @@
 click>=8.0.0
-deepgram-sdk>=6.0.0rc2
+deepgram-sdk>=7.5.0
 deepctl-core>=0.1.10
 deepctl-cmd-login>=0.1.10
 deepctl-cmd-projects>=0.1.10