Kokoro usage improvements by michalkulakowski · Pull Request #4357 · openvinotoolkit/model_server

michalkulakowski · 2026-07-03T13:56:19Z

🛠 Summary

JIRA/Issue if applicable.
Describe the changes.

🧪 Checklist

Unit tests added.
The documentation updated.
Change follows security best practices.
``

Copilot

Pull request overview

This PR updates Kokoro text-to-speech (TTS) integration by shifting voice embedding discovery to runtime (from the model directory) and moving espeak-ng from an OVMS binary dependency to a separately built artifact in Docker builds.

Changes:

Load Kokoro voice embeddings from <models_path>/voices/*.bin when the graph doesn’t explicitly specify voices.
Remove Bazel --//:espeak=on/off flag plumbing and build espeak-ng as an optional standalone Docker step (ARG ESPEAK=1/0).
Adjust tests and export tooling to align with the new Kokoro usage expectations.

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
windows_build.bat	Removes Bazel espeak flag wiring from Windows build invocation.
third_party/BUILD	Makes espeak-ng aliases unconditional (no build-flag select).
src/test/graph_export_test.cpp	Removes Kokoro voices list expectations and voices/ directory precreation.
src/test/audio/text2speech_test.cpp	Adds config validation test for missing `voices` in graph.
src/graph_export/graph_export.cpp	Stops enumerating Kokoro `voices/*.bin` into generated graph templates.
src/BUILD	Removes espeak-ng deps from the OVMS binary build.
src/audio/text_to_speech/t2s_servable.cpp	Implements fallback loading of embeddings from `<models_path>/voices` when graph voices are omitted.
src/audio/text_to_speech/t2s_calculator.cc	Minor comment cleanup in voice-selection error handling.
Makefile	Removes Bazel espeak flag usage; passes ESPEAK as a Docker build arg.
Dockerfile.ubuntu	Adds optional standalone Bazel build step for espeak-ng targets controlled by `ARG ESPEAK`.
Dockerfile.redhat	Same as Ubuntu Dockerfile: optional standalone espeak-ng build step.
distro.bzl	Removes the Bazel espeak build flag definition/config settings.
demos/common/export_models/export_model.py	Changes TTS exporter behavior, including default `--model_type`.
demos/audio/README.md	Adds documentation for ASR leaderboard-based transcription evaluation.
common_settings.bzl	Stops loading/creating the removed espeak flag config settings.

 #include <fstream>
 #include <sstream>
 #include <limits>
+#include <vector>


+static std::vector<std::filesystem::path> getVoiceEmbeddingPaths(const std::filesystem::path& voicesDir) {
+    std::vector<std::filesystem::path> voicePaths;
+    std::error_code ec;
+    for (const auto& entry : std::filesystem::directory_iterator(voicesDir, ec)) {
+        if (ec) {
+            throw std::runtime_error("Failed to iterate voices directory: " + voicesDir.string());
+        }
+        if (!entry.is_regular_file(ec) || ec) {
+            ec.clear();
+            continue;
+        }
+        if (entry.path().extension() == ".bin") {
+            voicePaths.emplace_back(entry.path());
+        }
+    }
+    std::sort(voicePaths.begin(), voicePaths.end());
+    return voicePaths;
+}


 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


+        [type.googleapis.com / mediapipe.T2sCalculatorOptions]: {
+            models_path: "/ovms/models_audio/Kokoro-82M"
+            plugin_config: '{"NUM_STREAMS": "1" }',
+            target_device: "CPU"
+        }
+        }


Copilot

Pull request overview

Copilot reviewed 18 out of 18 changed files in this pull request and generated 2 comments.

 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


dtrawins · 2026-07-08T10:01:31Z

+Kokoro is the primary example in this demo, but SpeechT5 remains supported for existing deployments.
 ### Model preparation
-Supported models should use the topology of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) which needs to be converted to IR format before using in OVMS.
+Supported models should use the topology of [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) and be converted to IR format before using in OVMS.


you can use https://huggingface.co/luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS/ till there is official model published

dtrawins · 2026-07-08T21:44:15Z

-> **Note:** Exporting `microsoft/speecht5_tts` model requires Python 3.10
-
-**CPU**
+Create the model directory:


this step is not needed - duplicated

dtrawins · 2026-07-08T21:45:27Z

 **Deploying on Bare Metal**

 ```bat
 mkdir models


on windows it's better to use c:\models

dtrawins · 2026-07-08T21:46:02Z

 ```bash
-mkdir -p models
-docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --model_path /models/microsoft/speecht5_tts --model_name microsoft/speecht5_tts
+docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --source_model luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS --model_repository_path /models --model_name Kokoro-82M-OpenVINO-FP16-OVMS


Suggested change

docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --source_model luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS --model_repository_path /models --model_name Kokoro-82M-OpenVINO-FP16-OVMS

mkdir models

docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --source_model luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS --model_repository_path /models --model_name Kokoro-82M-OpenVINO-FP16-OVMS

dtrawins · 2026-07-08T21:48:45Z

-The default configuration should work in most cases but the parameters can be tuned via `export_model.py` script arguments. Run the script with `--help` argument to check available parameters and see the [T2s calculator documentation](../../docs/speech_generation/reference.md) to learn more about configuration options and limitations.
+See the [T2s calculator documentation](../../docs/speech_generation/reference.md) to learn more about configuration options and limitations.

 ### Deployment


there should be included option for deployment on GPU and NPU

dtrawins · 2026-07-08T21:53:36Z

 if [ -n "$ESPEAK_DATA_SRC" ] && [ -d "$ESPEAK_DATA_SRC" ] ; then
    mkdir -p /ovms_release/share
    cp -rL "$ESPEAK_DATA_SRC" /ovms_release/share/ ;
+    chmod -R u+w /ovms_release/share/espeak-ng-data 2>/dev/null || true ;


add also a note in building from src doc with info that espeek is optional and can be delete from the package if not needed. explain the consequences - which language is supported without it

Copilot

Pull request overview

Copilot reviewed 20 out of 20 changed files in this pull request and generated 3 comments.

 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


+                    output.success = True
+                    output.latency = time.perf_counter() - st
+                    try:
+                        output.audio_duration = soundfile.info(io.BytesIO(audio_bytes)).duration
+                    except Exception:
+                        output.error = "Could not decode WAV response to compute audio duration"


michalkulakowski · 2026-07-13T11:41:59Z

+pip install -r https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/mkulakow/kokoro_improvements/demos/benchmark/v3/requirements.txt
+curl https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/mkulakow/kokoro_improvements/demos/benchmark/v3/benchmark.py -o benchmark.py
+python benchmark.py --api_url http://localhost:8000/v3/audio/speech --model Kokoro-82M-OpenVINO-FP16-OVMS --batch_size 1 --limit 100 --request_rate inf --backend text2speech --dataset edinburghcstr/ami --hf-subset ihm --voice af_alloy
+Number of documents: 1000


was added to check if it pass documentation tests and will be removed

mzegla · 2026-07-13T13:18:50Z

-Mean latency: 63653.98 ms
-Median latency: 66736.83 ms
-Average document length: 18.02 tokens
+pip install -r https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/mkulakow/kokoro_improvements/demos/benchmark/v3/requirements.txt


referencing branch

mzegla · 2026-07-13T13:19:04Z

-Median latency: 66736.83 ms
-Average document length: 18.02 tokens
+pip install -r https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/mkulakow/kokoro_improvements/demos/benchmark/v3/requirements.txt
+curl https://raw.githubusercontent.com/openvinotoolkit/model_server/refs/heads/mkulakow/kokoro_improvements/demos/benchmark/v3/benchmark.py -o benchmark.py


same as above

mzegla · 2026-07-13T13:42:45Z

-        std::filesystem::path voicePath(voice.path());
-        if (voicePath.is_relative()) {
-            voicePath = graphDir / voicePath;
+    if (!graphVoices.empty()) {


Do we need this check? If graphVoices is empty, there will be no iteration in below for anyway.

mzegla · 2026-07-13T13:44:30Z

+        return;
+    }
+
+    const std::filesystem::path voicesDir = parsedModelsPath / "voices";


"voices" -> const VOICES_DIR_NAME ?

mzegla · 2026-07-13T13:52:08Z

-if not exist "%repository%\%model%\openvino_tokenizer.bin" (
+if not exist "%repository%\%model%\openvino_model.xml" (
  echo Downloading %model_type% model to %repository%\%model% directory.
  python demos\common\export_models\export_model.py %model_type% --source_model "%model%" %export_args% --model_repository_path %repository%
 ) else (
-  echo Models file %repository%\%model%\openvino_tokenizer.bin exists. Skipping downloading models.
+  echo Models file %repository%\%model%\openvino_model.xml exists. Skipping downloading models.


Why is this change needed? Did you capture some practical gap?

Copilot

Pull request overview

Copilot reviewed 20 out of 20 changed files in this pull request and generated 7 comments.

+    const std::filesystem::path voicesDir = parsedModelsPath / VOICES_DIR_NAME;
+    std::error_code ec;
+    if (!std::filesystem::is_directory(voicesDir, ec)) {
+        SPDLOG_DEBUG("No voices configured in graph and voices directory not found: {}", voicesDir.string());
+        return;
+    }
+
+    for (const auto& voicePath : getVoiceEmbeddingPaths(voicesDir)) {
+        voices[voicePath.stem().string()] = readSpeakerEmbedding(voicePath, speakerEmbeddingShape);
+    }


 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


+                        audio_bytes.extend(chunk_bytes)
+                    output.success = True
+                    output.latency = time.perf_counter() - st
+                    try:
+                        output.audio_duration = soundfile.info(io.BytesIO(audio_bytes)).duration
+                    except Exception:
+                        output.error = "Could not decode WAV response to compute audio duration"


+static std::vector<std::filesystem::path> getVoiceEmbeddingPaths(const std::filesystem::path& voicesDir) {
+    std::vector<std::filesystem::path> voicePaths;
+    std::error_code errorCode;
+    std::filesystem::directory_iterator directoryIt(voicesDir, errorCode);
+    if (errorCode) {
+        throw std::runtime_error("Failed to open voices directory '" + voicesDir.string() + "': " + errorCode.message());
+    }


+    for (const auto& voicePath : getVoiceEmbeddingPaths(voicesDir)) {
+        voices[voicePath.stem().string()] = readSpeakerEmbedding(voicePath, speakerEmbeddingShape);
+    }


-**OVMS version 2025.4** This demo requires version 2025.4 or nightly release.
-
-**Model preparation**: Python 3.10 or higher with pip
+**OVMS version 2026.3** This demo require version 2026.3 or nightly release.


+### Optional `espeak-ng` for Speech Generation
+
+`espeak-ng` is optional in OVMS builds. It is used by Kokoro speech generation for:


Copilot

Pull request overview

Copilot reviewed 20 out of 20 changed files in this pull request and generated 5 comments.

+    const std::filesystem::path voicesDir = parsedModelsPath / VOICES_DIR_NAME;
+    std::error_code ec;
+    if (!std::filesystem::is_directory(voicesDir, ec)) {
+        SPDLOG_DEBUG("No voices configured in graph and voices directory not found: {}", voicesDir.string());
+        return;
+    }
+
+    for (const auto& voicePath : getVoiceEmbeddingPaths(voicesDir)) {
+        const std::string voiceName = voicePath.stem().string();
+        if (voices.find(voiceName) != voices.end()) {
+            SPDLOG_DEBUG("Voice '{}' is already configured and will be overwritten with tensor from: {}", voiceName, voicePath.string());
+        }
+        voices[voiceName] = readSpeakerEmbedding(voicePath, speakerEmbeddingShape);
+    }
+


 parser_text2speech = subparsers.add_parser('text2speech', help='export model for text2speech endpoint')
 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
 parser_text2speech.add_argument('--vocoder', type=str, help='The vocoder model to use for speecht5. For example microsoft/speecht5_hifigan. Ignored for kokoro.', dest='vocoder')
 parser_text2speech.add_argument('--speaker_name', type=str, help='Name of the speaker (speecht5 only; for kokoro all voices from the HF repo are exported).', dest='speaker_name')
 parser_text2speech.add_argument('--speaker_path', type=str, help='Path to the speaker.bin file (speecht5 only; for kokoro all voices from the HF repo are exported).', dest='speaker_path')


+> **Note:** `RTFx` (Real-Time Factor, inverted) is calculated as `generated_audio_duration / generation_time`.
+> Values greater than `1.0x` mean faster-than-real-time generation, while values below `1.0x` mean slower-than-real-time.


+#include <cstring>
+#include <filesystem>
+#include <fstream>
 #include <string>
+#include <vector>

 #include <gmock/gmock.h>
 #include <gtest/gtest.h>

+#include "google/protobuf/text_format.h"
+#include "mediapipe/framework/calculator.pb.h"
+
 #include "../../audio/audio_utils.hpp"
+#include "../../audio/text_to_speech/t2s_servable.hpp"
 #include "../../http_rest_api_handler.hpp"
 #include "../../server.hpp"
 #include "rapidjson/document.h"
 #include "../test_http_utils.hpp"
+#include "../test_with_temp_dir.hpp"
 #include "../test_utils.hpp"
 #include "../platform_utils.hpp"
 #include "../constructor_enabled_model_manager.hpp"


Copilot

Pull request overview

Copilot reviewed 20 out of 20 changed files in this pull request and generated 4 comments.

+    std::error_code ec;
+    if (!std::filesystem::is_directory(voicesDir, ec)) {
+        SPDLOG_DEBUG("Voices directory not found: {}", voicesDir.string());
+    }
+
+    for (const auto& voicePath : getVoiceEmbeddingPaths(voicesDir)) {
+        const std::string voiceName = voicePath.stem().string();
+        voices[voiceName] = readSpeakerEmbedding(voicePath, speakerEmbeddingShape);
+    }


 if [ "$2" = "docker" ]; then
    export PATH=$PATH:/opt/intel/openvino/python/bin
-    python3 -m pip install "optimum-intel"@git+https://github.com/huggingface/optimum-intel.git nncf sentence_transformers==5.3.0 sentencepiece requests protobuf==7.35.0
+    python3 -m pip install "optimum-intel"@git+https://github.com/huggingface/optimum-intel.git nncf sentence_transformers==5.3.0 sentencepiece requests protobuf==7.35.0 kokoro


 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


+> **Note:** `RTFx` (Real-Time Factor, inverted) is calculated as `generated_audio_duration / generation_time`.
+> Values greater than `1.0x` mean faster-than-real-time generation, while values below `1.0x` mean slower-than-real-time.
+


Copilot

Pull request overview

Copilot reviewed 20 out of 20 changed files in this pull request and generated 3 comments.

 add_common_arguments(parser_text2speech)
 parser_text2speech.add_argument('--num_streams', default=0, type=int, help='The number of parallel execution streams to use for the models in the pipeline.', dest='num_streams')
-parser_text2speech.add_argument('--model_type', default='speecht5', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')
+parser_text2speech.add_argument('--model_type', default='kokoro', choices=['speecht5', 'kokoro'], help='Type of the source TTS model. speecht5 uses optimum-cli; kokoro uses a dedicated PyTorch->OpenVINO conversion path.', dest='model_type')


+> **Note:** `RTFx` (Real-Time Factor, inverted) is calculated as `generated_audio_duration / generation_time`.
+> Values greater than `1.0x` mean faster-than-real-time generation, while values below `1.0x` mean slower-than-real-time.
+


Copilot AI review requested due to automatic review settings July 3, 2026 13:56

Copilot started reviewing on behalf of michalkulakowski July 3, 2026 13:56 View session

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch from 666f708 to 80f3156 Compare July 3, 2026 13:59

Copilot AI reviewed Jul 3, 2026

View reviewed changes

michalkulakowski requested a review from Copilot July 6, 2026 11:28

Copilot started reviewing on behalf of michalkulakowski July 6, 2026 11:29 View session

Copilot AI reviewed Jul 6, 2026

View reviewed changes

dtrawins reviewed Jul 8, 2026

View reviewed changes

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch from e118219 to 9dc3500 Compare July 8, 2026 14:30

dtrawins reviewed Jul 8, 2026

View reviewed changes

michalkulakowski requested a review from Copilot July 9, 2026 12:09

Copilot started reviewing on behalf of michalkulakowski July 9, 2026 12:11 View session

Copilot AI reviewed Jul 9, 2026

View reviewed changes

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch 2 times, most recently from 8ed0835 to 892d573 Compare July 13, 2026 11:52

mzegla reviewed Jul 13, 2026

View reviewed changes

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch from 892d573 to 9c5e4d1 Compare July 14, 2026 08:31

michalkulakowski requested review from Copilot, dtrawins and mzegla July 14, 2026 08:33

Copilot AI reviewed Jul 14, 2026

View reviewed changes

Copilot started reviewing on behalf of michalkulakowski July 14, 2026 08:52 View session

mzegla approved these changes Jul 14, 2026

View reviewed changes

michalkulakowski requested a review from Copilot July 14, 2026 09:43

Copilot started reviewing on behalf of michalkulakowski July 14, 2026 09:44 View session

Copilot AI reviewed Jul 14, 2026

View reviewed changes

michalkulakowski requested a review from Copilot July 14, 2026 11:33

Copilot started reviewing on behalf of michalkulakowski July 14, 2026 11:34 View session

Copilot AI reviewed Jul 14, 2026

View reviewed changes

dtrawins approved these changes Jul 14, 2026

View reviewed changes

michalkulakowski requested a review from Copilot July 14, 2026 12:16

Copilot started reviewing on behalf of michalkulakowski July 14, 2026 12:16 View session

Copilot AI reviewed Jul 14, 2026

View reviewed changes

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch 3 times, most recently from bcd0d07 to 08d0d5a Compare July 16, 2026 11:25

michalkulakowski added 5 commits July 16, 2026 14:37

Kokoro usage improvements

a3abf68

fix

3ab4b04

style

7e08645

style

052c200

fix

8ef6ad0

michalkulakowski force-pushed the mkulakow/kokoro_improvements branch from d4156a6 to 8ef6ad0 Compare July 16, 2026 12:38

fix

9f335c8

dtrawins added this to the 2026.3 milestone Jul 16, 2026

michalkulakowski added 2 commits July 16, 2026 19:53

fix

1583c90

fix

0c24a44

	docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --source_model luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS --model_repository_path /models --model_name Kokoro-82M-OpenVINO-FP16-OVMS
	mkdir models
	docker run -d -u $(id -u):$(id -g) --rm -p 8000:8000 -v $(pwd)/models:/models:rw openvino/model_server:latest --rest_port 8000 --source_model luis-castillo/Kokoro-82M-OpenVINO-FP16-OVMS --model_repository_path /models --model_name Kokoro-82M-OpenVINO-FP16-OVMS

		### Optional `espeak-ng` for Speech Generation

		`espeak-ng` is optional in OVMS builds. It is used by Kokoro speech generation for:

		> Note: `RTFx` (Real-Time Factor, inverted) is calculated as `generated_audio_duration / generation_time`.
		> Values greater than `1.0x` mean faster-than-real-time generation, while values below `1.0x` mean slower-than-real-time.

Uh oh!

Conversation

michalkulakowski commented Jul 3, 2026

🛠 Summary

🧪 Checklist

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants