memcat 1.0.0__tar.gz

memcat-1.0.0/LICENSE

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2026, Nous Labs
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

memcat-1.0.0/PKG-INFO

@@ -0,0 +1,198 @@
+Metadata-Version: 2.4
+Name: memcat
+Version: 1.0.0
+Summary: Clause-level text-to-speech cache for Pipecat voice bots.
+Keywords: pipecat,tts,text-to-speech,cache,voice,voice-ai,telephony
+Author: Umesh Yadav
+Author-email: Umesh Yadav <git@umesh.dev>
+License-Expression: BSD-2-Clause
+License-File: LICENSE
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Framework :: AsyncIO
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
+Classifier: Typing :: Typed
+Requires-Dist: pipecat-ai>=1.10,<1.14
+Requires-Dist: aiohttp>=3.11.12
+Requires-Dist: audioop-lts>=0.2.1 ; python_full_version >= '3.13'
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: numpy>=1.26.4
+Requires-Dist: soxr>=1.0.0
+Requires-Dist: memcat[redis,opus,s3] ; extra == 'all'
+Requires-Dist: av>=14 ; extra == 'opus'
+Requires-Dist: redis>=5.0.1 ; extra == 'redis'
+Requires-Dist: boto3>=1.34 ; extra == 's3'
+Requires-Python: >=3.11
+Project-URL: Homepage, https://github.com/imumesh18/memcat
+Project-URL: Source, https://github.com/imumesh18/memcat
+Project-URL: Documentation, https://github.com/imumesh18/memcat/tree/main/docs
+Project-URL: Changelog, https://github.com/imumesh18/memcat/blob/main/CHANGELOG.md
+Project-URL: Issues, https://github.com/imumesh18/memcat/issues
+Provides-Extra: all
+Provides-Extra: opus
+Provides-Extra: redis
+Provides-Extra: s3
+Description-Content-Type: text/markdown
+
+# Memcat
+
+**A text-to-speech cache for [Pipecat](https://github.com/pipecat-ai/pipecat) voice bots.**
+When your agent says a line it has said before (or part of one), Memcat replays the
+stored audio instead of paying the provider to synthesize it again, and the audio
+starts in milliseconds.
+
+| | Measured |
+| --- | --- |
+| Speech served from cache, scripted support calls ([Harper Valley Bank](https://github.com/cricketclub/gridspace-stanford-harper-valley), 1,446 calls) | **54.0% of characters, 59.0% of responses** |
+| Same, typed support chats ([ABCD](https://arxiv.org/abs/2104.00783), 10,042 chats) | 32.4% of characters, 38.5% of responses |
+| First audio of a sentence that opens with a cached clause, recorded ElevenLabs traffic | **2–13 ms** with Memcat vs 346 ms without (median, HTTP and WebSocket) |
+| What a listener hears, recorded ElevenLabs traffic, cached and live clauses mixed | the same words in the same order: 0.3% word error vs 0.0% without Memcat, by speech recognition |
+| First audio on a hit, local Kokoro voice | 1.0 ms from memory, 10 ms from Redis (vs 745 ms live) |
+| Added time on a miss | none measurable: 488 ms vs 495 ms without Memcat (median, within run-to-run noise) |
+| Storage per cached minute | 464 KB at 8 kHz (mu-law), 236 KB at 24 kHz (Opus) |
+| Cache keys containing a digit (order numbers, prices, dates, phone numbers) | **0** on all corpora |
+| Redis killed mid-call | every turn spoken, no error reaches the pipeline |
+
+Hit rates come from replaying public dialogue corpora through Memcat's own chunker,
+privacy rules and admission policy (`bench/hitrate.py`); no TTS was called. Net of
+what filling the cache costs, savings are within 2 points of these (54.0% and 31.9%).
+LLM agents whose every sentence carries an order number or a price cache less: 6–17%
+of characters on [τ²-bench](https://github.com/sierra-research/tau2-bench) traces,
+where those clauses stay live. The ElevenLabs rows replay traffic recorded from the
+ElevenLabs API (Flash v2.5) through Pipecat's ElevenLabs services
+(`bench/elevenlabs_replay.py`). The recordings are not in the repository; anyone with
+an ElevenLabs key can make their own and rerun it.
+
+## Install
+
+```bash
+uv add memcat                      # or: pip install memcat
+uv add "memcat[redis,opus]"        # shared cache across bot processes, compact audio
+```
+
+Python 3.11–3.13 and `pipecat-ai` 1.10–1.13. Extras: `redis` (`RedisStore`), `opus`
+(Opus storage), `s3` (`S3Store`), `all`.
+
+## Use
+
+```python
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from memcat import cached, MemcatConfig, RedisStore
+
+CachedCartesia = cached(CartesiaTTSService)   # once, at import time
+
+tts = CachedCartesia(
+    api_key=CARTESIA_API_KEY,
+    voice_id=VOICE_ID,
+    memcat=MemcatConfig(store=RedisStore(url=REDIS_URL), namespace="acme-support"),
+)
+```
+
+Use `tts` exactly as you used the unwrapped service. Nothing else in the pipeline
+changes. `await tts.memcat_stats()` reports hits, characters saved and dollars saved.
+
+No API keys at hand? From a clone, `uv run examples/kokoro_local.py` speaks three lines twice
+with a local voice; the second time they come from the cache.
+
+## How it works
+
+1. **Clauses, not just sentences.** Each sentence Pipecat hands to the TTS is split
+   at commas, semicolons, colons and dashes. "Thanks for waiting, your order 48213
+   has shipped, and it should arrive soon." is three clauses; the first and last are
+   reusable, the middle one is spoken live.
+2. **Privacy first.** A clause with any digit, a number in words, an email, a URL,
+   money, a date, a time or a spelled-out code is never cached. A clause is cached
+   only after it has been heard in 3 distinct calls, so a line said in one call never
+   enters the cache.
+3. **One lookup per sentence.** An in-process index answers misses with no network
+   call; hits come from memory or one Redis `MGET`.
+4. **Exact order on every provider.** On HTTP services cached and live audio
+   interleave inside one generator. On WebSocket services Memcat keeps Pipecat's
+   audio context and gives each run of live clauses its own provider stream,
+   releasing segments strictly in order, so cached clauses play before, between and
+   after live ones. Transcripts and word timestamps stay correct.
+5. **Joins matched to live speech.** Clips are stored tight and Memcat sets the pause
+   at each join the way live speech does (short after "Sure,", longer after a full
+   clause), matches loudness, and fades edges. Against live synthesis of the same
+   sentences, pauses differ by 45 ms at the median and loudness by at most 0.62 LU
+   (`bench/abx.py`).
+6. **Fill in the background.** A clause admitted from a live run that synthesized
+   it alone is stored as is, for free; others are rendered once by a background
+   copy of the same service. Nothing on the call ever waits for the cache.
+
+If the store, a codec or Memcat itself fails, the sentence goes to the provider as
+if Memcat were not installed: Memcat can lose savings, but the call goes on.
+
+## Providers
+
+| Provider | WebSocket | HTTP |
+| --- | --- | --- |
+| Cartesia | cached clauses anywhere in a sentence | cached clauses anywhere |
+| ElevenLabs | cached clauses anywhere | cached clauses anywhere, `previous_text` kept |
+| Deepgram Aura | cached clauses anywhere, within Deepgram's 20-flush/minute limit | cached clauses anywhere |
+| Sarvam | cached clauses before the first live one | cached clauses anywhere |
+| Any other Pipecat TTS service | cached clauses before the first live one (if it pushes its own start frames) | cached clauses anywhere (if it returns audio inline) |
+
+Every listed provider is tested with its Pipecat service class against a local
+emulator of the provider's wire protocol (`tests/emulators/`). ElevenLabs is also
+tested against recordings of its API, replayed with their original timing
+(`tests/test_replay_elevenlabs.py`). To record your own, see
+[CONTRIBUTING.md](https://github.com/imumesh18/memcat/blob/main/CONTRIBUTING.md).
+
+## Configure
+
+```python
+MemcatConfig(
+    store=RedisStore("redis://..."),   # default: one MemoryStore per process; RedisStore, S3Store
+    namespace="acme-support",          # tenant prefix on every key
+    admit_after_calls=3,               # distinct calls before a clause is cached
+    warm=["Thank you for calling ABC Shop, how can I help you today?"],  # cached at start
+    block_patterns=[r"\bACME-\w+"],    # extra text that must never be cached
+    ttl_s=30 * 24 * 3600,              # refreshed when served
+    codec="auto",                      # mu-law at 8 kHz, Opus when installed, else PCM16
+    enabled=True,                      # kill switch: False means a pure pass-through
+)
+```
+
+All fields are described in [docs/configuration.md](https://github.com/imumesh18/memcat/blob/main/docs/configuration.md).
+
+## Operate
+
+```bash
+memcat warm  --config memcat.toml --from calls.jsonl --top 500   # render your most repeated clauses
+memcat stats --config memcat.toml                                # entries, minutes, codecs
+memcat purge --config memcat.toml --text "..."                   # erase a text everywhere
+memcat export --config memcat.toml --to backup/ ; memcat import --config memcat.toml --from backup/
+memcat serve --config memcat.toml --port 8080                    # TTS endpoint for Vapi and other platforms
+```
+
+`memcat serve` puts the cache in front of hosted platforms that call a custom TTS
+URL (Vapi's custom voice): it answers with raw 16-bit PCM, streamed, and counts
+admission per platform call. It listens on 127.0.0.1 unless you set a secret (or
+pass `--insecure-no-auth` behind your own authentication).
+
+Every command except `serve` and `warm --dry-run` needs a Redis or S3 `[store]`.
+`purge --text` erases the text and each of its clauses in every voice, setting and
+sample rate; `purge --all` asks for confirmation (or `--yes`).
+
+See [docs/operations.md](https://github.com/imumesh18/memcat/blob/main/docs/operations.md) for `memcat.toml`, metrics and OpenTelemetry.
+
+## Benchmarks
+
+`bench/` reproduces every measured number above: `hitrate.py` (ABCD, Harper Valley
+Bank, τ²-bench), `elevenlabs_replay.py` (recorded ElevenLabs traffic), `latency.py`
+(Kokoro + Redis), `storage.py`, `hotpath.py` (run nightly, which fails at 3x
+its baseline), `soak.py` (100 concurrent calls) and `abx.py`, which builds a
+30-sentence listening test and measures each join against live speech. The Redis
+row is `tests/test_store_outage.py`. Results live in `bench/results/`.
+
+## License
+
+BSD 2-Clause, the same as Pipecat. Keep one cache (or one `namespace`) per
+customer so audio is never shared across customers, and check your provider's
+terms for anything else.

memcat-1.0.0/README.md

@@ -0,0 +1,157 @@
+# Memcat
+
+**A text-to-speech cache for [Pipecat](https://github.com/pipecat-ai/pipecat) voice bots.**
+When your agent says a line it has said before (or part of one), Memcat replays the
+stored audio instead of paying the provider to synthesize it again, and the audio
+starts in milliseconds.
+
+| | Measured |
+| --- | --- |
+| Speech served from cache, scripted support calls ([Harper Valley Bank](https://github.com/cricketclub/gridspace-stanford-harper-valley), 1,446 calls) | **54.0% of characters, 59.0% of responses** |
+| Same, typed support chats ([ABCD](https://arxiv.org/abs/2104.00783), 10,042 chats) | 32.4% of characters, 38.5% of responses |
+| First audio of a sentence that opens with a cached clause, recorded ElevenLabs traffic | **2–13 ms** with Memcat vs 346 ms without (median, HTTP and WebSocket) |
+| What a listener hears, recorded ElevenLabs traffic, cached and live clauses mixed | the same words in the same order: 0.3% word error vs 0.0% without Memcat, by speech recognition |
+| First audio on a hit, local Kokoro voice | 1.0 ms from memory, 10 ms from Redis (vs 745 ms live) |
+| Added time on a miss | none measurable: 488 ms vs 495 ms without Memcat (median, within run-to-run noise) |
+| Storage per cached minute | 464 KB at 8 kHz (mu-law), 236 KB at 24 kHz (Opus) |
+| Cache keys containing a digit (order numbers, prices, dates, phone numbers) | **0** on all corpora |
+| Redis killed mid-call | every turn spoken, no error reaches the pipeline |
+
+Hit rates come from replaying public dialogue corpora through Memcat's own chunker,
+privacy rules and admission policy (`bench/hitrate.py`); no TTS was called. Net of
+what filling the cache costs, savings are within 2 points of these (54.0% and 31.9%).
+LLM agents whose every sentence carries an order number or a price cache less: 6–17%
+of characters on [τ²-bench](https://github.com/sierra-research/tau2-bench) traces,
+where those clauses stay live. The ElevenLabs rows replay traffic recorded from the
+ElevenLabs API (Flash v2.5) through Pipecat's ElevenLabs services
+(`bench/elevenlabs_replay.py`). The recordings are not in the repository; anyone with
+an ElevenLabs key can make their own and rerun it.
+
+## Install
+
+```bash
+uv add memcat                      # or: pip install memcat
+uv add "memcat[redis,opus]"        # shared cache across bot processes, compact audio
+```
+
+Python 3.11–3.13 and `pipecat-ai` 1.10–1.13. Extras: `redis` (`RedisStore`), `opus`
+(Opus storage), `s3` (`S3Store`), `all`.
+
+## Use
+
+```python
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from memcat import cached, MemcatConfig, RedisStore
+
+CachedCartesia = cached(CartesiaTTSService)   # once, at import time
+
+tts = CachedCartesia(
+    api_key=CARTESIA_API_KEY,
+    voice_id=VOICE_ID,
+    memcat=MemcatConfig(store=RedisStore(url=REDIS_URL), namespace="acme-support"),
+)
+```
+
+Use `tts` exactly as you used the unwrapped service. Nothing else in the pipeline
+changes. `await tts.memcat_stats()` reports hits, characters saved and dollars saved.
+
+No API keys at hand? From a clone, `uv run examples/kokoro_local.py` speaks three lines twice
+with a local voice; the second time they come from the cache.
+
+## How it works
+
+1. **Clauses, not just sentences.** Each sentence Pipecat hands to the TTS is split
+   at commas, semicolons, colons and dashes. "Thanks for waiting, your order 48213
+   has shipped, and it should arrive soon." is three clauses; the first and last are
+   reusable, the middle one is spoken live.
+2. **Privacy first.** A clause with any digit, a number in words, an email, a URL,
+   money, a date, a time or a spelled-out code is never cached. A clause is cached
+   only after it has been heard in 3 distinct calls, so a line said in one call never
+   enters the cache.
+3. **One lookup per sentence.** An in-process index answers misses with no network
+   call; hits come from memory or one Redis `MGET`.
+4. **Exact order on every provider.** On HTTP services cached and live audio
+   interleave inside one generator. On WebSocket services Memcat keeps Pipecat's
+   audio context and gives each run of live clauses its own provider stream,
+   releasing segments strictly in order, so cached clauses play before, between and
+   after live ones. Transcripts and word timestamps stay correct.
+5. **Joins matched to live speech.** Clips are stored tight and Memcat sets the pause
+   at each join the way live speech does (short after "Sure,", longer after a full
+   clause), matches loudness, and fades edges. Against live synthesis of the same
+   sentences, pauses differ by 45 ms at the median and loudness by at most 0.62 LU
+   (`bench/abx.py`).
+6. **Fill in the background.** A clause admitted from a live run that synthesized
+   it alone is stored as is, for free; others are rendered once by a background
+   copy of the same service. Nothing on the call ever waits for the cache.
+
+If the store, a codec or Memcat itself fails, the sentence goes to the provider as
+if Memcat were not installed: Memcat can lose savings, but the call goes on.
+
+## Providers
+
+| Provider | WebSocket | HTTP |
+| --- | --- | --- |
+| Cartesia | cached clauses anywhere in a sentence | cached clauses anywhere |
+| ElevenLabs | cached clauses anywhere | cached clauses anywhere, `previous_text` kept |
+| Deepgram Aura | cached clauses anywhere, within Deepgram's 20-flush/minute limit | cached clauses anywhere |
+| Sarvam | cached clauses before the first live one | cached clauses anywhere |
+| Any other Pipecat TTS service | cached clauses before the first live one (if it pushes its own start frames) | cached clauses anywhere (if it returns audio inline) |
+
+Every listed provider is tested with its Pipecat service class against a local
+emulator of the provider's wire protocol (`tests/emulators/`). ElevenLabs is also
+tested against recordings of its API, replayed with their original timing
+(`tests/test_replay_elevenlabs.py`). To record your own, see
+[CONTRIBUTING.md](https://github.com/imumesh18/memcat/blob/main/CONTRIBUTING.md).
+
+## Configure
+
+```python
+MemcatConfig(
+    store=RedisStore("redis://..."),   # default: one MemoryStore per process; RedisStore, S3Store
+    namespace="acme-support",          # tenant prefix on every key
+    admit_after_calls=3,               # distinct calls before a clause is cached
+    warm=["Thank you for calling ABC Shop, how can I help you today?"],  # cached at start
+    block_patterns=[r"\bACME-\w+"],    # extra text that must never be cached
+    ttl_s=30 * 24 * 3600,              # refreshed when served
+    codec="auto",                      # mu-law at 8 kHz, Opus when installed, else PCM16
+    enabled=True,                      # kill switch: False means a pure pass-through
+)
+```
+
+All fields are described in [docs/configuration.md](https://github.com/imumesh18/memcat/blob/main/docs/configuration.md).
+
+## Operate
+
+```bash
+memcat warm  --config memcat.toml --from calls.jsonl --top 500   # render your most repeated clauses
+memcat stats --config memcat.toml                                # entries, minutes, codecs
+memcat purge --config memcat.toml --text "..."                   # erase a text everywhere
+memcat export --config memcat.toml --to backup/ ; memcat import --config memcat.toml --from backup/
+memcat serve --config memcat.toml --port 8080                    # TTS endpoint for Vapi and other platforms
+```
+
+`memcat serve` puts the cache in front of hosted platforms that call a custom TTS
+URL (Vapi's custom voice): it answers with raw 16-bit PCM, streamed, and counts
+admission per platform call. It listens on 127.0.0.1 unless you set a secret (or
+pass `--insecure-no-auth` behind your own authentication).
+
+Every command except `serve` and `warm --dry-run` needs a Redis or S3 `[store]`.
+`purge --text` erases the text and each of its clauses in every voice, setting and
+sample rate; `purge --all` asks for confirmation (or `--yes`).
+
+See [docs/operations.md](https://github.com/imumesh18/memcat/blob/main/docs/operations.md) for `memcat.toml`, metrics and OpenTelemetry.
+
+## Benchmarks
+
+`bench/` reproduces every measured number above: `hitrate.py` (ABCD, Harper Valley
+Bank, τ²-bench), `elevenlabs_replay.py` (recorded ElevenLabs traffic), `latency.py`
+(Kokoro + Redis), `storage.py`, `hotpath.py` (run nightly, which fails at 3x
+its baseline), `soak.py` (100 concurrent calls) and `abx.py`, which builds a
+30-sentence listening test and measures each join against live speech. The Redis
+row is `tests/test_store_outage.py`. Results live in `bench/results/`.
+
+## License
+
+BSD 2-Clause, the same as Pipecat. Keep one cache (or one `namespace`) per
+customer so audio is never shared across customers, and check your provider's
+terms for anything else.

memcat-1.0.0/pyproject.toml

@@ -0,0 +1,155 @@
+[project]
+name = "memcat"
+version = "1.0.0"
+description = "Clause-level text-to-speech cache for Pipecat voice bots."
+readme = "README.md"
+license = "BSD-2-Clause"
+license-files = ["LICENSE"]
+requires-python = ">=3.11"
+keywords = [
+    "pipecat",
+    "tts",
+    "text-to-speech",
+    "cache",
+    "voice",
+    "voice-ai",
+    "telephony",
+]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Framework :: AsyncIO",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Typing :: Typed",
+]
+dependencies = [
+    "pipecat-ai>=1.10,<1.14",
+    "aiohttp>=3.11.12",
+    "audioop-lts>=0.2.1; python_version >= '3.13'",
+    "loguru>=0.7.3",
+    "numpy>=1.26.4",
+    "soxr>=1.0.0",
+]
+
+[[project.authors]]
+name = "Umesh Yadav"
+email = "git@umesh.dev"
+
+[project.optional-dependencies]
+redis = ["redis>=5.0.1"]
+opus = ["av>=14"]
+s3 = ["boto3>=1.34"]
+all = ["memcat[redis,opus,s3]"]
+
+[project.scripts]
+memcat = "memcat.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/imumesh18/memcat"
+Source = "https://github.com/imumesh18/memcat"
+Documentation = "https://github.com/imumesh18/memcat/tree/main/docs"
+Changelog = "https://github.com/imumesh18/memcat/blob/main/CHANGELOG.md"
+Issues = "https://github.com/imumesh18/memcat/issues"
+
+[dependency-groups]
+asr = ["faster-whisper>=1.2.1"]
+dev = [
+    "pytest>=8",
+    "pytest-asyncio>=0.24",
+    "pytest-cov>=5",
+    "hypothesis>=6.100",
+    "ruff>=0.6",
+    "pyright>=1.1.380",
+    "redis>=5.0.1",
+    "av>=14",
+    "boto3>=1.34",
+    "moto[s3]>=5",
+    "opentelemetry-api>=1.20",
+    "opentelemetry-sdk>=1.20",
+    "pipecat-ai[kokoro]>=1.13.0,<1.14",
+    "psutil>=7.2.2",
+]
+
+[build-system]
+requires = ["uv_build>=0.13.1,<0.14.0"]
+build-backend = "uv_build"
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.format]
+exclude = ["*.md"]
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "W",
+    "I",
+    "B",
+    "UP",
+    "SIM",
+    "RUF",
+    "ASYNC",
+    "PERF",
+    "S",
+]
+ignore = [
+    "S101",
+    "S311",
+    "RUF012",
+    "RUF001",
+    "RUF002",
+    "RUF003",
+    "ASYNC109",
+    "ASYNC110",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = [
+    "S",
+    "B",
+    "PERF",
+    "RUF",
+    "ASYNC",
+]
+"bench/**" = [
+    "S",
+    "PERF",
+    "RUF",
+    "ASYNC",
+]
+"examples/**" = ["S"]
+
+[tool.pyright]
+include = ["src"]
+pythonVersion = "3.11"
+typeCheckingMode = "strict"
+reportMissingTypeStubs = false
+reportUnknownMemberType = false
+reportUnknownVariableType = false
+reportUnknownArgumentType = false
+reportUnknownParameterType = false
+reportMissingParameterType = false
+reportPrivateUsage = false
+reportUnnecessaryIsInstance = false
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+testpaths = ["tests"]
+filterwarnings = ["ignore::DeprecationWarning"]
+
+[tool.coverage.run]
+source = ["memcat"]
+branch = true
+
+[tool.coverage.report]
+show_missing = true
+skip_covered = true

memcat-1.0.0/pyproject.toml.orig

@@ -0,0 +1,116 @@
+[project]
+name = "memcat"
+version = "1.0.0"
+description = "Clause-level text-to-speech cache for Pipecat voice bots."
+readme = "README.md"
+license = "BSD-2-Clause"
+license-files = ["LICENSE"]
+authors = [{ name = "Umesh Yadav", email = "git@umesh.dev" }]
+requires-python = ">=3.11"
+keywords = ["pipecat", "tts", "text-to-speech", "cache", "voice", "voice-ai", "telephony"]
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Framework :: AsyncIO",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Multimedia :: Sound/Audio :: Speech",
+    "Typing :: Typed",
+]
+dependencies = [
+    "pipecat-ai>=1.10,<1.14",  # each Pipecat minor is tested before it is allowed
+    # Imported directly by memcat; Pipecat 1.10 requires the same floors.
+    "aiohttp>=3.11.12",
+    "audioop-lts>=0.2.1; python_version >= '3.13'",
+    "loguru>=0.7.3",
+    "numpy>=1.26.4",
+    "soxr>=1.0.0",
+]
+
+[project.optional-dependencies]
+redis = ["redis>=5.0.1"]
+opus = ["av>=14"]
+s3 = ["boto3>=1.34"]
+all = ["memcat[redis,opus,s3]"]
+
+[project.scripts]
+memcat = "memcat.cli:main"
+
+[project.urls]
+Homepage = "https://github.com/imumesh18/memcat"
+Source = "https://github.com/imumesh18/memcat"
+Documentation = "https://github.com/imumesh18/memcat/tree/main/docs"
+Changelog = "https://github.com/imumesh18/memcat/blob/main/CHANGELOG.md"
+Issues = "https://github.com/imumesh18/memcat/issues"
+
+[dependency-groups]
+asr = [
+    "faster-whisper>=1.2.1",
+]
+dev = [
+    "pytest>=8",
+    "pytest-asyncio>=0.24",
+    "pytest-cov>=5",
+    "hypothesis>=6.100",
+    "ruff>=0.6",
+    "pyright>=1.1.380",
+    "redis>=5.0.1",
+    "av>=14",
+    "boto3>=1.34",
+    "moto[s3]>=5",
+    "opentelemetry-api>=1.20",
+    "opentelemetry-sdk>=1.20",
+    "pipecat-ai[kokoro]>=1.13.0,<1.14",
+    "psutil>=7.2.2",
+]
+
+[build-system]
+requires = ["uv_build>=0.13.1,<0.14.0"]
+build-backend = "uv_build"
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+
+[tool.ruff.format]
+# Ruff also formats Python blocks in Markdown; the docs keep hand-aligned comments.
+exclude = ["*.md"]
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "B", "UP", "SIM", "RUF", "ASYNC", "PERF", "S"]
+ignore = ["S101", "S311", "RUF012", "RUF001", "RUF002", "RUF003", "ASYNC109", "ASYNC110"]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["S", "B", "PERF", "RUF", "ASYNC"]
+"bench/**" = ["S", "PERF", "RUF", "ASYNC"]
+"examples/**" = ["S"]
+
+[tool.pyright]
+include = ["src"]
+pythonVersion = "3.11"
+typeCheckingMode = "strict"
+reportMissingTypeStubs = false
+reportUnknownMemberType = false
+reportUnknownVariableType = false
+reportUnknownArgumentType = false
+reportUnknownParameterType = false
+reportMissingParameterType = false
+reportPrivateUsage = false
+reportUnnecessaryIsInstance = false
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+testpaths = ["tests"]
+filterwarnings = ["ignore::DeprecationWarning"]
+
+[tool.coverage.run]
+source = ["memcat"]
+branch = true
+
+[tool.coverage.report]
+show_missing = true
+skip_covered = true