cogno-vox 0.1.0__tar.gz

cogno_vox-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Sudoers AI
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cogno_vox-0.1.0/PKG-INFO

@@ -0,0 +1,152 @@
+Metadata-Version: 2.4
+Name: cogno-vox
+Version: 0.1.0
+Summary: Voice/audio I/O edge for the Cogno cognitive pipeline — speech-to-text (STT) in, text-to-speech (TTS) out, with provider-agnostic fallback chains
+Author: Sudoers AI
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/sudoers-ai/cogno-vox
+Project-URL: Repository, https://github.com/sudoers-ai/cogno-vox
+Project-URL: Issues, https://github.com/sudoers-ai/cogno-vox/issues
+Keywords: llm,stt,tts,whisper,speech-to-text,text-to-speech,voice,agents
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+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 :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Operating System :: OS Independent
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: httpx>=0.24
+Requires-Dist: cogno-homeo<0.2,>=0.1
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0; extra == "dev"
+Requires-Dist: ruff>=0.5; extra == "dev"
+Requires-Dist: mypy>=1.8; extra == "dev"
+Requires-Dist: fastapi>=0.110; extra == "dev"
+Requires-Dist: httpx>=0.27; extra == "dev"
+Provides-Extra: bedrock
+Requires-Dist: boto3>=1.34; extra == "bedrock"
+Provides-Extra: server
+Requires-Dist: fastapi>=0.110; extra == "server"
+Requires-Dist: uvicorn>=0.29; extra == "server"
+Dynamic: license-file
+
+# cogno-vox
+
+**Voice/audio I/O edge for the [Cogno](https://github.com/sudoers-ai/cogno-anima) cognitive pipeline** — speech-to-text in, text-to-speech out, behind provider-agnostic fallback chains.
+
+`cogno-vox` is the *mouth and ears* of Cogno. Where [`cogno-anima`](https://github.com/sudoers-ai/cogno-anima) is the *mind* (pure cognition) and [`cogno-engram`](https://github.com/sudoers-ai/cogno-engram) is the *memory* (persistence substrate), `cogno-vox` is the **transport edge** that sits on the two boundaries of the pipeline:
+
+```
+gateway ──▶ [vox STT] ──▶ cogno-anima (NOUMENO…SUPEREGO) ──▶ [vox TTS] ──▶ gateway
+             audio→text                                        text→audio
+```
+
+It is the most decoupled of the libraries: the core imports **neither** `cogno-anima` **nor** `cogno-engram` — it only converts audio ⇆ text.
+
+> Status: **alpha** — core (ports + OpenAI-compatible backends + fallback chains) and the unit suite are in place.
+
+## Two capability-scoped ports
+
+Like `cogno-anima`'s `LLMBackend`/`Embedder` and `cogno-engram`'s three ports, each direction is a structurally-typed `Protocol` with its own fallback chain (try tier 1→N, first non-empty wins, all-fail → raises):
+
+| Port | Async method | Reference backends |
+| --- | --- | --- |
+| `TranscriberBackend` (STT) | `transcribe(audio, filename) -> str` | OpenAI-compatible (faster-whisper-server / Groq / OpenAI), Gemini multimodal, Bedrock/Voxtral |
+| `SynthesizerBackend` (TTS) | `synthesize(text) -> bytes` | OpenAI-compatible (Kokoro / OpenAI), Grok, ElevenLabs, Gemini |
+
+`OpenAICompat*` covers any `/v1/audio/transcriptions` or `/v1/audio/speech` server — local or cloud differ only by `base_url`/`api_key`, no SDK needed (just `httpx`).
+
+## Async by design
+
+Everything is `async` (`httpx.AsyncClient`) to run under concurrent request load alongside `cogno-anima`/`cogno-engram`. Provider SDKs are lazy-imported behind extras (`pip install "cogno-vox[bedrock]"`); the OpenAI-compatible HTTP path needs no extra.
+
+## Host-injected config (no YAML, no env contextvar)
+
+The host owns tier selection (model ladder, per-tenant routing, BYOK). You hand the factory a `VoxConfig`:
+
+```python
+from cogno_vox import VoxConfig, TierConfig, create_transcriber, create_synthesizer
+
+config = VoxConfig(
+    transcribe_tiers=(
+        TierConfig(provider="local", model="Systran/faster-whisper-small",
+                   base_url="http://localhost:8000"),
+        TierConfig(provider="groq", model="whisper-large-v3-turbo",
+                   base_url="https://api.groq.com/openai/v1", api_key="gsk_..."),
+    ),
+    synthesize_tiers=(
+        TierConfig(provider="local", model="kokoro",
+                   base_url="http://localhost:8880/v1", voice="af_alloy"),
+        TierConfig(provider="openai", model="tts-1", voice="alloy",
+                   base_url="https://api.openai.com/v1", api_key="sk-..."),
+    ),
+    default_tts_format="opus",   # mandatory for Telegram native voice notes
+)
+
+stt = await create_transcriber(config).transcribe(audio_bytes, "voice.ogg")
+print(stt.text, stt.tier, stt.elapsed_ms)
+
+out = await create_synthesizer(config).synthesize("Olá, tudo bem?")
+# out.audio (bytes), out.fmt, out.tier, out.elapsed_ms
+```
+
+`split_text_for_tts()` slices long replies into ~30s segments (≈65 words) at sentence boundaries — one voice note each.
+
+## What stays in the host
+
+Provider/model selection, RBAC premium gating, BYOK & key rotation, the channel delivery (`sendVoice`/`sendMedia`) and the channel-mandated format choice. `cogno-vox` offers `opus`/`mp3`; the host decides.
+
+## The Cogno ecosystem
+
+`cogno-vox` is one organ of **[Cogno](https://github.com/sudoers-ai)** — a family of
+small, composable, Apache-2.0 libraries that together form a complete
+conversational-agent platform. Each library owns a single concern and stays
+infra-agnostic; a **host** assembles them into a running agent:
+
+![The Cogno ecosystem](docs/assets/cogno-ecosystem.svg)
+
+The open-source libraries are the organs; the **host is the body** that joins
+them. Our reference host — `cogno-host`, with its `cogno-ui` dashboard — is the
+private product layer, but it holds no special powers: everything it does rides
+on the public seams documented in each library's `docs/HOST_INTEGRATION.md`, so
+you can assemble a body of your own.
+
+## Develop
+
+```bash
+pip install -e ".[dev]"
+pytest tests/unit -q          # mocked HTTP, no network
+ruff check cogno_vox && mypy cogno_vox
+```
+
+### Live integration tests (gated, auto-skip)
+
+`tests/integration` runs end-to-end against real local servers and **auto-skips**
+unless pointed at them (same pattern as `cogno-engram`'s `ENGRAM_TEST_DSN`).
+Validated against `fedirz/faster-whisper-server` (`Systran/faster-whisper-small`)
+and `ghcr.io/remsky/kokoro-fastapi-cpu`. The bundled `docker-compose.yml` brings
+both up:
+
+```bash
+docker compose up -d           # whisper :8000, kokoro :8880
+
+VOX_TEST_WHISPER_URL=http://localhost:8000 \
+VOX_TEST_KOKORO_URL=http://localhost:8880/v1 \
+pytest tests/integration -q   # synth (Kokoro) -> transcribe (Whisper) round-trip
+```
+
+See [`docs/HOST_INTEGRATION.md`](docs/HOST_INTEGRATION.md) for wiring `cogno-vox`
+onto the two edges of the pipeline.
+
+## License
+
+Apache-2.0.

cogno_vox-0.1.0/README.md

@@ -0,0 +1,111 @@
+# cogno-vox
+
+**Voice/audio I/O edge for the [Cogno](https://github.com/sudoers-ai/cogno-anima) cognitive pipeline** — speech-to-text in, text-to-speech out, behind provider-agnostic fallback chains.
+
+`cogno-vox` is the *mouth and ears* of Cogno. Where [`cogno-anima`](https://github.com/sudoers-ai/cogno-anima) is the *mind* (pure cognition) and [`cogno-engram`](https://github.com/sudoers-ai/cogno-engram) is the *memory* (persistence substrate), `cogno-vox` is the **transport edge** that sits on the two boundaries of the pipeline:
+
+```
+gateway ──▶ [vox STT] ──▶ cogno-anima (NOUMENO…SUPEREGO) ──▶ [vox TTS] ──▶ gateway
+             audio→text                                        text→audio
+```
+
+It is the most decoupled of the libraries: the core imports **neither** `cogno-anima` **nor** `cogno-engram` — it only converts audio ⇆ text.
+
+> Status: **alpha** — core (ports + OpenAI-compatible backends + fallback chains) and the unit suite are in place.
+
+## Two capability-scoped ports
+
+Like `cogno-anima`'s `LLMBackend`/`Embedder` and `cogno-engram`'s three ports, each direction is a structurally-typed `Protocol` with its own fallback chain (try tier 1→N, first non-empty wins, all-fail → raises):
+
+| Port | Async method | Reference backends |
+| --- | --- | --- |
+| `TranscriberBackend` (STT) | `transcribe(audio, filename) -> str` | OpenAI-compatible (faster-whisper-server / Groq / OpenAI), Gemini multimodal, Bedrock/Voxtral |
+| `SynthesizerBackend` (TTS) | `synthesize(text) -> bytes` | OpenAI-compatible (Kokoro / OpenAI), Grok, ElevenLabs, Gemini |
+
+`OpenAICompat*` covers any `/v1/audio/transcriptions` or `/v1/audio/speech` server — local or cloud differ only by `base_url`/`api_key`, no SDK needed (just `httpx`).
+
+## Async by design
+
+Everything is `async` (`httpx.AsyncClient`) to run under concurrent request load alongside `cogno-anima`/`cogno-engram`. Provider SDKs are lazy-imported behind extras (`pip install "cogno-vox[bedrock]"`); the OpenAI-compatible HTTP path needs no extra.
+
+## Host-injected config (no YAML, no env contextvar)
+
+The host owns tier selection (model ladder, per-tenant routing, BYOK). You hand the factory a `VoxConfig`:
+
+```python
+from cogno_vox import VoxConfig, TierConfig, create_transcriber, create_synthesizer
+
+config = VoxConfig(
+    transcribe_tiers=(
+        TierConfig(provider="local", model="Systran/faster-whisper-small",
+                   base_url="http://localhost:8000"),
+        TierConfig(provider="groq", model="whisper-large-v3-turbo",
+                   base_url="https://api.groq.com/openai/v1", api_key="gsk_..."),
+    ),
+    synthesize_tiers=(
+        TierConfig(provider="local", model="kokoro",
+                   base_url="http://localhost:8880/v1", voice="af_alloy"),
+        TierConfig(provider="openai", model="tts-1", voice="alloy",
+                   base_url="https://api.openai.com/v1", api_key="sk-..."),
+    ),
+    default_tts_format="opus",   # mandatory for Telegram native voice notes
+)
+
+stt = await create_transcriber(config).transcribe(audio_bytes, "voice.ogg")
+print(stt.text, stt.tier, stt.elapsed_ms)
+
+out = await create_synthesizer(config).synthesize("Olá, tudo bem?")
+# out.audio (bytes), out.fmt, out.tier, out.elapsed_ms
+```
+
+`split_text_for_tts()` slices long replies into ~30s segments (≈65 words) at sentence boundaries — one voice note each.
+
+## What stays in the host
+
+Provider/model selection, RBAC premium gating, BYOK & key rotation, the channel delivery (`sendVoice`/`sendMedia`) and the channel-mandated format choice. `cogno-vox` offers `opus`/`mp3`; the host decides.
+
+## The Cogno ecosystem
+
+`cogno-vox` is one organ of **[Cogno](https://github.com/sudoers-ai)** — a family of
+small, composable, Apache-2.0 libraries that together form a complete
+conversational-agent platform. Each library owns a single concern and stays
+infra-agnostic; a **host** assembles them into a running agent:
+
+![The Cogno ecosystem](docs/assets/cogno-ecosystem.svg)
+
+The open-source libraries are the organs; the **host is the body** that joins
+them. Our reference host — `cogno-host`, with its `cogno-ui` dashboard — is the
+private product layer, but it holds no special powers: everything it does rides
+on the public seams documented in each library's `docs/HOST_INTEGRATION.md`, so
+you can assemble a body of your own.
+
+## Develop
+
+```bash
+pip install -e ".[dev]"
+pytest tests/unit -q          # mocked HTTP, no network
+ruff check cogno_vox && mypy cogno_vox
+```
+
+### Live integration tests (gated, auto-skip)
+
+`tests/integration` runs end-to-end against real local servers and **auto-skips**
+unless pointed at them (same pattern as `cogno-engram`'s `ENGRAM_TEST_DSN`).
+Validated against `fedirz/faster-whisper-server` (`Systran/faster-whisper-small`)
+and `ghcr.io/remsky/kokoro-fastapi-cpu`. The bundled `docker-compose.yml` brings
+both up:
+
+```bash
+docker compose up -d           # whisper :8000, kokoro :8880
+
+VOX_TEST_WHISPER_URL=http://localhost:8000 \
+VOX_TEST_KOKORO_URL=http://localhost:8880/v1 \
+pytest tests/integration -q   # synth (Kokoro) -> transcribe (Whisper) round-trip
+```
+
+See [`docs/HOST_INTEGRATION.md`](docs/HOST_INTEGRATION.md) for wiring `cogno-vox`
+onto the two edges of the pipeline.
+
+## License
+
+Apache-2.0.

cogno_vox-0.1.0/cogno_vox/__init__.py

@@ -0,0 +1,64 @@
+"""cogno-vox — voice/audio I/O edge for the Cogno cognitive pipeline.
+
+STT before the mind, TTS after it:
+    gateway -> [vox STT] -> cogno-anima -> [vox TTS] -> gateway
+
+The core imports neither cogno-anima nor cogno-engram — it only converts
+audio <-> text behind two capability-scoped protocols with provider-agnostic
+fallback chains.
+"""
+
+from cogno_vox.chunker import split_text_for_tts
+from cogno_vox.factory import create_synthesizer, create_transcriber
+from cogno_vox.text_prep import apply_emotion, clean_text_for_tts, strip_emotion_tags
+from cogno_vox.ports import (
+    SynthesisError,
+    SynthesizerBackend,
+    TranscriberBackend,
+    TranscriptionError,
+    VoxError,
+)
+from cogno_vox.synthesizer import (
+    ElevenLabsSynthesizer,
+    FallbackSynthesizer,
+    GeminiSynthesizer,
+    GrokSynthesizer,
+    OpenAICompatSynthesizer,
+)
+from cogno_vox.transcriber import (
+    BedrockTranscriber,
+    FallbackTranscriber,
+    GeminiTranscriber,
+    OpenAICompatTranscriber,
+)
+from cogno_vox.types import (
+    SUPPORTED_INPUT_FORMATS,
+    SynthesisResult,
+    TierConfig,
+    TranscriptionResult,
+    VoxConfig,
+)
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "__version__",
+    # ports + errors
+    "TranscriberBackend", "SynthesizerBackend",
+    "VoxError", "TranscriptionError", "SynthesisError",
+    # types
+    "VoxConfig", "TierConfig", "TranscriptionResult", "SynthesisResult",
+    "SUPPORTED_INPUT_FORMATS",
+    # chains
+    "FallbackTranscriber", "FallbackSynthesizer",
+    # transcriber backends
+    "OpenAICompatTranscriber", "GeminiTranscriber", "BedrockTranscriber",
+    # synthesizer backends
+    "OpenAICompatSynthesizer", "GrokSynthesizer",
+    "ElevenLabsSynthesizer", "GeminiSynthesizer",
+    # factory + utils
+    "create_transcriber", "create_synthesizer", "split_text_for_tts",
+    "apply_emotion",
+    "clean_text_for_tts",
+    "strip_emotion_tags",
+]

cogno_vox-0.1.0/cogno_vox/audio_utils.py

@@ -0,0 +1,97 @@
+"""
+cogno_vox.audio_utils — audio container helpers.
+
+Currently: raw PCM → Opus-in-Ogg via an ffmpeg subprocess. Gemini TTS returns
+Linear16 PCM @ 24kHz; Telegram (and most voice-note channels) expect Opus.
+
+ffmpeg is a *soft* dependency: if it is not on PATH the function degrades by
+returning the raw PCM unchanged (the caller/channel may still accept it, or the
+fallback chain moves on) rather than raising.
+"""
+
+from __future__ import annotations
+
+import logging
+import shutil
+import subprocess
+
+log = logging.getLogger(__name__)
+
+
+def ffmpeg_available() -> bool:
+    """True when the ``ffmpeg`` binary is on PATH. Used for a boot-time check: the local Kokoro
+    tier re-encodes opus via ffmpeg (``wav_to_opus``), and its degrade is STRICT (``b""``), so a
+    missing ffmpeg silently kills all voice output — worth surfacing at startup, not per turn."""
+    return shutil.which("ffmpeg") is not None
+
+
+def pcm_to_opus(pcm: bytes, sample_rate: int = 24000) -> bytes:
+    """Convert raw signed-16-bit mono PCM to Opus-in-Ogg via ffmpeg.
+
+    Returns the original ``pcm`` unchanged if ffmpeg is unavailable or fails.
+    """
+    if not pcm:
+        return b""
+    try:
+        result = subprocess.run(
+            [
+                "ffmpeg", "-y",
+                "-f", "s16le",           # signed 16-bit little-endian
+                "-ar", str(sample_rate),
+                "-ac", "1",              # mono
+                "-i", "pipe:0",
+                "-c:a", "libopus",
+                "-b:a", "32k",
+                "-f", "ogg",
+                "pipe:1",
+            ],
+            input=pcm,
+            capture_output=True,
+            timeout=30,
+        )
+        if result.returncode == 0 and result.stdout:
+            return result.stdout
+        log.warning("ffmpeg PCM->Opus failed: rc=%d stderr=%s",
+                    result.returncode, result.stderr[:200])
+        return pcm
+    except FileNotFoundError:
+        log.warning("ffmpeg not found — returning raw PCM")
+        return pcm
+    except Exception as exc:
+        log.warning("PCM->Opus conversion error: %s", exc)
+        return pcm
+
+
+def wav_to_opus(audio: bytes) -> bytes:
+    """Convert a container-carrying audio blob (WAV/anything ffmpeg sniffs) to Opus-in-Ogg.
+
+    Companion to :func:`pcm_to_opus` for sources that return a full container instead of raw
+    PCM — e.g. requesting ``wav`` from a Kokoro server (whose own ``opus`` encoder truncates
+    the tail of the audio) and encoding properly here.
+
+    Degrade contract is STRICT (unlike ``pcm_to_opus``): on ffmpeg failure it returns ``b""``.
+    The caller promised opus (``fmt`` is reported to the channel, which labels the voice note
+    ``audio/ogg``) — handing back WAV under that label breaks playback outright, whereas an
+    empty result makes the tier fail over to the next engine (or degrade to a text reply).
+    """
+    if not audio:
+        return b""
+    try:
+        result = subprocess.run(
+            ["ffmpeg", "-y", "-i", "pipe:0",
+             "-c:a", "libopus", "-b:a", "32k", "-f", "ogg", "pipe:1"],
+            input=audio,
+            capture_output=True,
+            timeout=30,
+        )
+        if result.returncode == 0 and result.stdout:
+            return result.stdout
+        log.warning("ffmpeg WAV->Opus failed: rc=%d stderr=%s",
+                    result.returncode, result.stderr[:200])
+        return b""
+    except FileNotFoundError:
+        log.warning("ffmpeg not found — WAV->Opus unavailable, failing the tier over")
+        return b""
+    except Exception as exc:
+        log.warning("WAV->Opus conversion error: %s", exc)
+        return b""