Lokaler Kokoro-82M-Text-to-Speech-MCP-Server. Wenn Ihr Agent speak aufruft, synthetisiert er Sprache und spielt sie auf Ihrem Rechner ab, sodass Sie den Harness sprechen hören können.
Funktioniert mit jedem MCP-Client: Claude Desktop, Claude Code, Cursor, VS Code, opencode, Cline und mehr. Ein kurzer Konfigurationsblock, keine API-Schlüssel – die Synthese läuft lokal mit Kokoro-82M.
Beim ersten Start stellt der Server zwei Dinge bereit, die nicht auf PyPI sind: die Kokoro-82M-Gewichte (~312 MB) in einen lokalen Cache und das englische spaCy-Modell (en_core_web_sm) in dieselbe Python-Umgebung, in der der Server läuft. Diese zweite Installation ist erforderlich, da Kokoros G2P-Pipeline spaCy lädt und eine uvx-/uv tool-Umgebung das Modell nicht enthält, es sei denn, dieses Paket legt es dort ab.
Fügen Sie Folgendes zur MCP-Konfiguration Ihres Clients hinzu:
{
"mcpServers": {
"mcp-kokoro-tts": {
"command": "uvx",
"args": ["mcp-kokoro-tts"]
}
}
}Erfordert Python 3.12 und uv. Der erste Serverstart stellt Kokoro-Gewichte und das englische spaCy-Modell automatisch bereit.
Um beide vorab herunterzuladen, ohne den MCP-Server zu starten:
uvx mcp-kokoro-tts-provisionRelated MCP server: MCP TTS Server
Fügen Sie eine Zeile zu Ihrer AGENTS.md / CLAUDE.md / Systemaufforderung hinzu:
When the user wants to hear something spoken aloud, call the `speak` tool with clear, natural text.speakSynthetisiert Sprache, schreibt eine WAV-Datei und spielt sie lokal ab.
Param | Erforderlich | Beschreibung |
| ja | Zu sprechender Text (max. 500 Zeichen) |
| nein | Stimm-ID (z. B. |
| nein | Wiedergabegeschwindigkeits-Multiplikator (Standard |
list_voicesListet verfügbare Kokoro-Stimmen und die aktuell ausgewählte Standardstimme auf.
Auflösungsreihenfolge:
TTS_VOICE-Umgebungsvariable – Stimm-ID oder absoluter .pt-Pfad
Eine Datei im voices/-Ordner des Pakets, deren Name mit default beginnt
Erste .pt-Datei in voices/ (alphabetisch)
Die gebündelte af_heart-Stimme des Modells
{
"mcpServers": {
"mcp-kokoro-tts": {
"command": "uvx",
"args": ["mcp-kokoro-tts"],
"env": {
"TTS_VOICE": "af_heart"
}
}
}
}Variable | Beschreibung |
| Standard-Stimm-ID oder absoluter |
| Modell-Cache-Verzeichnis überschreiben |
| Hugging-Face-Hub-Cache-Verzeichnis überschreiben |
| Verzeichnis für generierte WAV-Dateien |
| Auf |
| Optionales Hugging-Face-Token für schnellere Downloads |
OS | Synthese | Wiedergabe |
macOS | ja |
|
Linux | ja |
|
Windows | ja | PowerShell |
espeak-ng ist optional. Englisch funktioniert ohne es; installieren Sie es für eine bessere Abdeckung von Wörtern außerhalb des Vokabulars und einige nicht-englische Sprachen.
Das Taggen einer Version führt GitHub Actions publish.yml aus, das zuerst auf PyPI und dann in die MCP-Registry hochlädt.
Die Veröffentlichung auf PyPI verwendet das Repo-Geheimnis PYPI_TOKEN (ein PyPI-API-Token). GitHub Trusted Publishing kann auch auf dem PyPI-Projekt konfiguriert werden; dieser Workflow authentifiziert sich mit dem Token, sodass eine erste Veröffentlichung nicht von der Übereinstimmung mit einem ausstehenden Publisher abhängt.
version in pyproject.toml erhöhen (und server.json, falls Sie noch nicht taggen)
Committen und taggen: git tag v0.1.2 && git push origin v0.1.2
GitHub Actions führt publish.yml aus:
release – Typprüfung, Tests, Wheel/sdist bauen
pypi-publish – Upload zu PyPI mit PYPI_TOKEN
mcp-registry – OIDC → MCP-Registry (nach erfolgreichem PyPI-Upload)
cd mcps-tts
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pyright
pytest
python -m mcp_kokoro_ttsApache-2.0. Siehe LICENSE und NOTICE. Die Kokoro-82M-Modellgewichte werden separat unter ihrer Apache-2.0-Lizenz heruntergeladen.
List Kokoro voices available to the speak tool and the currently selected default voice. Resolution order: TTS_VOICE env var, voices/default* file, first file in voices/, then the model's default af_heart voice.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does exceptionally well: it reveals the exact resolution order (env var, file, first file, fallback model default), which behaviorally affects what the tool returns. This is precisely the kind of contextual detail an agent needs beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, the first clearly scopes the listing and the second enumerates the resolution order. Every phrase adds value and the default-voice resolution rule is stated in a compact, order-relevant manner.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description does not need to explain return format. It fully explains what this tool does (list voices and default voice) and even how the default is determined, which is the behavioral nuance essential for an agent to pick the right voice via speak.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so the schema is already complete (100% coverage) and there is nothing for the description to elaborate on. Baseline 4 applies since there is simply no parameter information needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('List') and resource ('Kokoro voices available to the speak tool') and also includes the currently selected default voice. The mention of 'speak tool' clearly distinguishes it from the sibling speak tool, making its function unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool should be used to discover available voice options before using the speak tool, especially because it names the speak tool as the consumer. It clearly states the resolution order for the default voice, giving immediate context, but it does not explicitly say when not to use it or mention alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Synthesize speech with Kokoro-82M and play it on the user's machine. Call this when the user wants the harness to talk, read something aloud, or hear a spoken response. Always pass clear, natural text to speak. Default voice resolution: TTS_VOICE env var, voices/default* in the package, first file in voices/, then the bundled af_heart voice from the model.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| speed | No | ||
| voice | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it makes a reasonable effort. It discloses the side effect of audio playback ('play it on the user's machine') and thoroughly documents the voice resolution fallback order (TTS_VOICE env var, voices/default*, first file in voices/, then af_heart). However, it doesn't disclose potential blocking behavior, absence of audio hardware, or other side effects that could be expected given the nature of the tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, with the core purpose front-loaded first and the resolution detail last. Every sentence earns its place — the usage guidance and voice resolution order are both essential for the agent. The voice resolution sentence is dense but packs critical behavioral information. A slight trim could occur since the resolution order could be seen as implementation detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description captures the core essence—synth and play, when to trigger, how voice is resolved—which is solid for a 3-parameter tool. No annotations or schema descriptions exist to offload this burden to. Missing context includes behavior of the speed parameter, the relationship to the sibling list_voices, and failure modes. Given the total absence of annotations and schema descriptions, the description could do more to guide an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description needed to compensate, and it partially does. It adds value for the text parameter ('clear, natural text to speak') and implicitly for the voice parameter by explaining the resolution order. However, the speed parameter is entirely unexplained (what units, what range), and the voice format is only hinted at. Given the extremely low schema coverage, this partial compensation keeps it at a decent but not exceptional level.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource ('Synthesize speech with Kokoro-82M and play it on the user's machine') that clearly identifies what the tool does. It goes further to elaborate intended use cases ('when the user wants the harness to talk, read something aloud, or hear a spoken response'). It doesn't explicitly contrast itself with the sibling list_voices, which keeps it just short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance with concrete examples ('when the user wants the harness to talk, read something aloud, or hear a spoken response'). It includes a practical instruction to 'Always pass clear, natural text to speak.' However, it stops short of explicitly naming alternatives (e.g., list_voices) for comparison or stating when not to use it, so it lacks the explicit exclusions of a perfect score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.4list_voicesspeakScored across 2 tools
The two tools have clearly distinct purposes: one performs speech synthesis ('speak'), the other lists available voices ('list_voices'). No ambiguity between them, as they serve complementary roles in the TTS workflow.
Both tool names follow an imperative verb style ('speak', 'list_voices'), which is concise and predictable. 'list_voices' uses a verb_noun pattern, but the naming is consistent in tone and clarity for a small set.
With only 2 tools, the server is minimal yet well-scoped for its purpose: a text-to-speech harness. The count is appropriate; additional tools would likely be redundant.
The core operation (speak) is present, and the companion list_voices provides necessary context for voice selection. Minor gaps exist, such as no pause/stop or voice configuration tool, but these are not critical for basic TTS functionality.
MCP server for Text-to-Speech
AI voice generation: text-to-speech and voice cloning from any MCP client.
MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)
MCP server for Speech-to-Text
