Use this file to discover all available pages before exploring further.

Text-to-speech

OpenClaw can convert outbound replies into audio across 14 speech providers and deliver native voice messages on Feishu, Matrix, Telegram, and WhatsApp, audio attachments everywhere else, and PCM/Ulaw streams for telephony and Talk.

Quick start

Pick a provider

OpenAI and ElevenLabs are the most reliable hosted options. Microsoft and Local CLI work without an API key. See the [provider matrix](#supported-providers) for the full list.

Set the API key

Export the env var for your provider (for example `OPENAI_API_KEY`, `ELEVENLABS_API_KEY`). Microsoft and Local CLI need no key.

Enable in config

Set `messages.tts.auto: "always"` and `messages.tts.provider`:


text
```json5}
{
  messages: {
    tts: {
      auto: "always",
      provider: "elevenlabs",
    },
  },
}
```

Try it in chat

`/tts status` shows the current state. `/tts audio Hello from OpenClaw` sends a one-off audio reply.

note

Auto-TTS is **off** by default. When `messages.tts.provider` is unset, OpenClaw picks the first configured provider in registry auto-select order.

Supported providers

Provider	Auth	Notes
Azure Speech	text `AZURE_SPEECH_KEY` + text `AZURE_SPEECH_REGION` (also text `AZURE_SPEECH_API_KEY` , text `SPEECH_KEY` , text `SPEECH_REGION` )	Native Ogg/Opus voice-note output and telephony.
DeepInfra	text `DEEPINFRA_API_KEY`	OpenAI-compatible TTS. Defaults to text `hexgrad/Kokoro-82M` .
ElevenLabs	text `ELEVENLABS_API_KEY` or text `XI_API_KEY`	Voice cloning, multilingual, deterministic via text `seed` .
Google Gemini	text `GEMINI_API_KEY` or text `GOOGLE_API_KEY`	Gemini API TTS; persona-aware via text `promptTemplate: "audio-profile-v1"` .
Gradium	text `GRADIUM_API_KEY`	Voice-note and telephony output.
Inworld	text `INWORLD_API_KEY`	Streaming TTS API. Native Opus voice-note and PCM telephony.
Local CLI	none	Runs a configured local TTS command.
Microsoft	none	Public Edge neural TTS via text `node-edge-tts` . Best-effort, no SLA.
MiniMax	text `MINIMAX_API_KEY` (or Token Plan: text `MINIMAX_OAUTH_TOKEN` , text `MINIMAX_CODE_PLAN_KEY` , text `MINIMAX_CODING_API_KEY` )	T2A v2 API. Defaults to text `speech-2.8-hd` .
OpenAI	text `OPENAI_API_KEY`	Also used for auto-summary; supports persona text `instructions` .
OpenRouter	text `OPENROUTER_API_KEY` (can reuse text `models.providers.openrouter.apiKey` )	Default model text `hexgrad/kokoro-82m` .
Volcengine	text `VOLCENGINE_TTS_API_KEY` or text `BYTEPLUS_SEED_SPEECH_API_KEY` (legacy AppID/token: text `VOLCENGINE_TTS_APPID` / text `_TOKEN` )	BytePlus Seed Speech HTTP API.
Vydra	text `VYDRA_API_KEY`	Shared image, video, and speech provider.
xAI	text `XAI_API_KEY`	xAI batch TTS. Native Opus voice-note is not supported.
Xiaomi MiMo	text `XIAOMI_API_KEY`	MiMo TTS through Xiaomi chat completions.

If multiple providers are configured, the selected one is used first and the others are fallback options. Auto-summary uses

text

summaryModel

(or

text

agents.defaults.model.primary

), so that provider must also be authenticated if you keep summaries enabled.

warning

The bundled **Microsoft** provider uses Microsoft Edge's online neural TTS service via `node-edge-tts`. It is a public web service without a published SLA or quota — treat it as best-effort. The legacy provider id `edge` is normalized to `microsoft` and `openclaw doctor --fix` rewrites persisted config; new configs should always use `microsoft`.

Configuration

TTS config lives under

text

messages.tts

text

~/.openclaw/openclaw.json

. Pick a preset and adapt the provider block:

```json5} { messages: { tts: { auto: "always", provider: "azure-speech", providers: { "azure-speech": { apiKey: "${AZURE_SPEECH_KEY}", region: "eastus", voice: "en-US-JennyNeural", lang: "en-US", outputFormat: "audio-24khz-48kbitrate-mono-mp3", voiceNoteOutputFormat: "ogg-24khz-16bit-mono-opus", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "elevenlabs", providers: { elevenlabs: { apiKey: "${ELEVENLABS_API_KEY}", model: "eleven_multilingual_v2", voiceId: "EXAVITQu4vr4xnSDxMaL", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "google", providers: { google: { apiKey: "${GEMINI_API_KEY}", model: "gemini-3.1-flash-tts-preview", voiceName: "Kore", // Optional natural-language style prompts: // audioProfile: "Speak in a calm, podcast-host tone.", // speakerName: "Alex", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "gradium", providers: { gradium: { apiKey: "${GRADIUM_API_KEY}", voiceId: "YTpq7expH9539ERJ", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "inworld", providers: { inworld: { apiKey: "${INWORLD_API_KEY}", modelId: "inworld-tts-1.5-max", voiceId: "Sarah", temperature: 0.7, }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "tts-local-cli", providers: { "tts-local-cli": { command: "say", args: ["-o", "{{OutputPath}}", "{{Text}}"], outputFormat: "wav", timeoutMs: 120000, }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "microsoft", providers: { microsoft: { enabled: true, voice: "en-US-MichelleNeural", lang: "en-US", outputFormat: "audio-24khz-48kbitrate-mono-mp3", rate: "+0%", pitch: "+0%", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "minimax", providers: { minimax: { apiKey: "${MINIMAX_API_KEY}", model: "speech-2.8-hd", voiceId: "English_expressive_narrator", speed: 1.0, vol: 1.0, pitch: 0, }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "openai", summaryModel: "openai/gpt-4.1-mini", modelOverrides: { enabled: true }, providers: { openai: { apiKey: "${OPENAI_API_KEY}", model: "gpt-4o-mini-tts", voice: "alloy", }, elevenlabs: { apiKey: "${ELEVENLABS_API_KEY}", model: "eleven_multilingual_v2", voiceId: "EXAVITQu4vr4xnSDxMaL", voiceSettings: { stability: 0.5, similarityBoost: 0.75, style: 0.0, useSpeakerBoost: true, speed: 1.0 }, applyTextNormalization: "auto", languageCode: "en", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "openrouter", providers: { openrouter: { apiKey: "${OPENROUTER_API_KEY}", model: "hexgrad/kokoro-82m", voice: "af_alloy", responseFormat: "mp3", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "volcengine", providers: { volcengine: { apiKey: "${VOLCENGINE_TTS_API_KEY}", resourceId: "seed-tts-1.0", voice: "en_female_anna_mars_bigtts", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "xai", providers: { xai: { apiKey: "${XAI_API_KEY}", voiceId: "eve", language: "en", responseFormat: "mp3", }, }, }, }, } ``` ```json5} { messages: { tts: { auto: "always", provider: "xiaomi", providers: { xiaomi: { apiKey: "${XIAOMI_API_KEY}", model: "mimo-v2.5-tts", voice: "mimo_default", format: "mp3", }, }, }, }, } ```

Per-agent voice overrides

Use

text

agents.list[].tts

when one agent should speak with a different provider, voice, model, persona, or auto-TTS mode. The agent block deep-merges over

text

messages.tts

, so provider credentials can stay in the global provider config:


json5
{
  messages: {
    tts: {
      auto: "always",
      provider: "elevenlabs",
      providers: {
        elevenlabs: { apiKey: "${ELEVENLABS_API_KEY}", model: "eleven_multilingual_v2" },
      },
    },
  },
  agents: {
    list: [
      {
        id: "reader",
        tts: {
          providers: {
            elevenlabs: { voiceId: "EXAVITQu4vr4xnSDxMaL" },
          },
        },
      },
    ],
  },
}

To pin a per-agent persona, set

text

agents.list[].tts.persona

alongside provider config — it overrides the global

text

messages.tts.persona

for that agent only.

Precedence order for automatic replies,

text

/tts audio

text

/tts status

, and the

text

tts

agent tool:

text
messages.tts
active
text
agents.list[].tts
channel override, when the channel supports
text
channels.<channel>.tts
account override, when the channel passes
text
channels.<channel>.accounts.<id>.tts
local
text
/tts
preferences for this host
inline
text
[[tts:...]]
directives when model overrides are enabled

Channel and account overrides use the same shape as

text

messages.tts

and deep-merge over the earlier layers, so shared provider credentials can stay in

text

messages.tts

while a channel or bot account changes only voice, model, persona, or auto mode:


json5
{
  messages: {
    tts: {
      provider: "openai",
      providers: {
        openai: { apiKey: "${OPENAI_API_KEY}", model: "gpt-4o-mini-tts" },
      },
    },
  },
  channels: {
    feishu: {
      accounts: {
        english: {
          tts: {
            providers: {
              openai: { voice: "shimmer" },
            },
          },
        },
      },
    },
  },
}

Personas

A persona is a stable spoken identity that can be applied deterministically across providers. It can prefer one provider, define provider-neutral prompt intent, and carry provider-specific bindings for voices, models, prompt templates, seeds, and voice settings.

Minimal persona


json5
{
  messages: {
    tts: {
      auto: "always",
      persona: "narrator",
      personas: {
        narrator: {
          label: "Narrator",
          provider: "elevenlabs",
          providers: {
            elevenlabs: { voiceId: "EXAVITQu4vr4xnSDxMaL", modelId: "eleven_multilingual_v2" },
          },
        },
      },
    },
  },
}

Full persona (provider-neutral prompt)


json5
{
  messages: {
    tts: {
      auto: "always",
      persona: "alfred",
      personas: {
        alfred: {
          label: "Alfred",
          description: "Dry, warm British butler narrator.",
          provider: "google",
          fallbackPolicy: "preserve-persona",
          prompt: {
            profile: "A brilliant British butler. Dry, witty, warm, charming, emotionally expressive, never generic.",
            scene: "A quiet late-night study. Close-mic narration for a trusted operator.",
            sampleContext: "The speaker is answering a private technical request with concise confidence and dry warmth.",
            style: "Refined, understated, lightly amused.",
            accent: "British English.",
            pacing: "Measured, with short dramatic pauses.",
            constraints: ["Do not read configuration values aloud.", "Do not explain the persona."],
          },
          providers: {
            google: {
              model: "gemini-3.1-flash-tts-preview",
              voiceName: "Algieba",
              promptTemplate: "audio-profile-v1",
            },
            openai: { model: "gpt-4o-mini-tts", voice: "cedar" },
            elevenlabs: {
              voiceId: "voice_id",
              modelId: "eleven_multilingual_v2",
              seed: 42,
              voiceSettings: {
                stability: 0.65,
                similarityBoost: 0.8,
                style: 0.25,
                useSpeakerBoost: true,
                speed: 0.95,
              },
            },
          },
        },
      },
    },
  },
}

Persona resolution

The active persona is selected deterministically:

text
/tts persona <id>
local preference, if set.
text
messages.tts.persona
, if set.
No persona.

Provider selection runs explicit-first:

Direct overrides (CLI, gateway, Talk, allowed TTS directives).
text
/tts provider <id>
local preference.
Active persona's
text
provider
.
text
messages.tts.provider
.
Registry auto-select.

For each provider attempt, OpenClaw merges configs in this order:

text
messages.tts.providers.<id>
text
messages.tts.personas.<persona>.providers.<id>
Trusted request overrides
Allowed model-emitted TTS directive overrides

How providers use persona prompts

Persona prompt fields (

text

profile

text

scene

text

sampleContext

text

style

text

accent

text

pacing

text

constraints

) are provider-neutral. Each provider decides how to use them:

Fallback policy

text

fallbackPolicy

controls behavior when a persona has no binding for the attempted provider:

Policy	Behavior
text `preserve-persona`	Default. Provider-neutral prompt fields stay available; the provider may use them or ignore them.
text `provider-defaults`	Persona is omitted from prompt preparation for that attempt; the provider uses its neutral defaults while fallback to other providers continues.
text `fail`	Skip that provider attempt with text `reasonCode: "not_configured"` and text `personaBinding: "missing"` . Fallback providers are still tried.

The whole TTS request only fails when every attempted provider is skipped or fails.

Model-driven directives

By default, the assistant can emit

text

[[tts:...]]

directives to override voice, model, or speed for a single reply, plus an optional

text

[[tts:text]]...[[/tts:text]]

block for expressive cues that should appear in audio only:


text
Here you go.

[[tts:voiceId=pMsXgVXv3BLzUgSXRplE model=eleven_v3 speed=1.1]]
[[tts:text]](laughs) Read the song once more.[[/tts:text]]

When

text

messages.tts.auto

text

"tagged"

, directives are required to trigger audio. Streaming block delivery strips directives from visible text before the channel sees them, even when split across adjacent blocks.

text

provider=...

is ignored unless

text

modelOverrides.allowProvider: true

. When a reply declares

text

provider=...

, the other keys in that directive are parsed only by that provider; unsupported keys are stripped and reported as TTS directive warnings.

Available directive keys:

text
provider
(registered provider id; requires
text
allowProvider: true
)
text
voice
/
text
voiceName
/
text
voice_name
/
text
google_voice
/
text
voiceId
text
model
/
text
google_model
text
stability
,
text
similarityBoost
,
text
style
,
text
speed
,
text
useSpeakerBoost
text
vol
/
text
volume
(MiniMax volume, 0–10)
text
pitch
(MiniMax integer pitch, −12 to 12; fractional values are truncated)
text
emotion
(Volcengine emotion tag)
text
applyTextNormalization
(
text
auto|on|off
)
text
languageCode
(ISO 639-1)
text
seed

Disable model overrides entirely:


json5
{ messages: { tts: { modelOverrides: { enabled: false } } } }

Allow provider switching while keeping other knobs configurable:


json5
{ messages: { tts: { modelOverrides: { enabled: true, allowProvider: true, allowSeed: false } } } }

Slash commands

Single command

text

/tts

. On Discord, OpenClaw also registers

text

/voice

because

text

/tts

is a built-in Discord command — text

text

/tts ...

still works.


text
/tts off | on | status
/tts chat on | off | default
/tts latest
/tts provider <id>
/tts persona <id> | off
/tts limit <chars>
/tts summary off
/tts audio <text>

note

Commands require an authorized sender (allowlist/owner rules apply) and either `commands.text` or native command registration must be enabled.

Behavior notes:

text
/tts on
writes the local TTS preference to
text
always
;
text
/tts off
writes it to
text
off
.
text
/tts chat on|off|default
writes a session-scoped auto-TTS override for the current chat.
text
/tts persona <id>
writes the local persona preference;
text
/tts persona off
clears it.
text
/tts latest
reads the latest assistant reply from the current session transcript and sends it as audio once. It stores only a hash of that reply on the session entry to suppress duplicate voice sends.
text
/tts audio
generates a one-off audio reply (does not toggle TTS on).
text
limit
and
text
summary
are stored in local prefs, not the main config.
text
/tts status
includes fallback diagnostics for the latest attempt —
text
Fallback: <primary> -> <used>
,
text
Attempts: ...
, and per-attempt detail (
text
provider:outcome(reasonCode) latency
).
text
/status
shows the active TTS mode plus configured provider, model, voice, and sanitized custom endpoint metadata when TTS is enabled.

Per-user preferences

Slash commands write local overrides to

text

prefsPath

. The default is

text

~/.openclaw/settings/tts.json

; override with the

text

OPENCLAW_TTS_PREFS

env var or

text

messages.tts.prefsPath

Stored field	Effect
text `auto`	Local auto-TTS override ( text `always` , text `off` , …)
text `provider`	Local primary provider override
text `persona`	Local persona override
text `maxLength`	Summary threshold (default text `1500` chars)
text `summarize`	Summary toggle (default text `true` )

These override the effective config from

text

messages.tts

plus the active

text

agents.list[].tts

block for that host.

Output formats (fixed)

TTS voice delivery is channel-capability driven. Channel plugins advertise whether voice-style TTS should ask providers for a native

text

voice-note

target or keep normal

text

audio-file

synthesis and only mark compatible output for voice delivery.

Voice-note capable channels: voice-note replies prefer Opus (
text
opus_48000_64
from ElevenLabs,
text
opus
from OpenAI).
- 48kHz / 64kbps is a good voice message tradeoff.
Feishu / WhatsApp: when a voice-note reply is produced as MP3/WebM/WAV/M4A or another likely audio file, the channel plugin transcodes it to 48kHz Ogg/Opus with
text
ffmpeg
before sending the native voice message. WhatsApp sends the result through the Baileys
text
audio
payload with
text
ptt: true
and
text
audio/ogg; codecs=opus
. If conversion fails, Feishu receives the original file as an attachment; WhatsApp send fails rather than posting an incompatible PTT payload.
BlueBubbles: keeps provider synthesis on the normal audio-file path; MP3 and CAF outputs are marked for iMessage voice memo delivery.
Other channels: MP3 (
text
mp3_44100_128
from ElevenLabs,
text
mp3
from OpenAI).
- 44.1kHz / 128kbps is the default balance for speech clarity.
MiniMax: MP3 (
text
speech-2.8-hd
model, 32kHz sample rate) for normal audio attachments. For channel-advertised voice-note targets, OpenClaw transcodes the MiniMax MP3 to 48kHz Opus with
text
ffmpeg
before delivery when the channel advertises transcoding.
Xiaomi MiMo: MP3 by default, or WAV when configured. For channel-advertised voice-note targets, OpenClaw transcodes Xiaomi output to 48kHz Opus with
text
ffmpeg
before delivery when the channel advertises transcoding.
Local CLI: uses the configured
text
outputFormat
. Voice-note targets are converted to Ogg/Opus and telephony output is converted to raw 16 kHz mono PCM with
text
ffmpeg
.
Google Gemini: Gemini API TTS returns raw 24kHz PCM. OpenClaw wraps it as WAV for audio attachments, transcodes it to 48kHz Opus for voice-note targets, and returns PCM directly for Talk/telephony.
Gradium: WAV for audio attachments, Opus for voice-note targets, and
text
ulaw_8000
at 8 kHz for telephony.
Inworld: MP3 for normal audio attachments, native
text
OGG_OPUS
for voice-note targets, and raw
text
PCM
at 22050 Hz for Talk/telephony.
xAI: MP3 by default;
text
responseFormat
may be
text
mp3
,
text
wav
,
text
pcm
,
text
mulaw
, or
text
alaw
. OpenClaw uses xAI's batch REST TTS endpoint and returns a complete audio attachment; xAI's streaming TTS WebSocket is not used by this provider path. Native Opus voice-note format is not supported by this path.
Microsoft: uses
text
microsoft.outputFormat
(default
text
audio-24khz-48kbitrate-mono-mp3
).
- The bundled transport accepts an
  text
  outputFormat
  , but not all formats are available from the service.
- Output format values follow Microsoft Speech output formats (including Ogg/WebM Opus).
- Telegram
  text
  sendVoice
  accepts OGG/MP3/M4A; use OpenAI/ElevenLabs if you need guaranteed Opus voice messages.
- If the configured Microsoft output format fails, OpenClaw retries with MP3.

OpenAI/ElevenLabs output formats are fixed per channel (see above).

Auto-TTS behavior

When

text

messages.tts.auto

is enabled, OpenClaw:

Skips TTS if the reply already contains media or a
text
MEDIA:
directive.
Skips very short replies (under 10 chars).
Summarizes long replies when summaries are enabled, using
text
summaryModel
(or
text
agents.defaults.model.primary
).
Attaches the generated audio to the reply.
In
text
mode: "final"
, still sends audio-only TTS for streamed final replies after the text stream completes; the generated media goes through the same channel media normalization as normal reply attachments.

If the reply exceeds

text

maxLength

and summary is off (or no API key for the summary model), audio is skipped and the normal text reply is sent.


text
Reply -> TTS enabled?
  no  -> send text
  yes -> has media / MEDIA: / short?
          yes -> send text
          no  -> length > limit?
                   no  -> TTS -> attach audio
                   yes -> summary enabled?
                            no  -> send text
                            yes -> summarize -> TTS -> attach audio

Output formats by channel

Target	Format
Feishu / Matrix / Telegram / WhatsApp	Voice-note replies prefer Opus ( text `opus_48000_64` from ElevenLabs, text `opus` from OpenAI). 48 kHz / 64 kbps balances clarity and size.
Other channels	MP3 ( text `mp3_44100_128` from ElevenLabs, text `mp3` from OpenAI). 44.1 kHz / 128 kbps default for speech.
Talk / telephony	Provider-native PCM (Inworld 22050 Hz, Google 24 kHz), or text `ulaw_8000` from Gradium for telephony.

Per-provider notes:

Feishu / WhatsApp transcoding: When a voice-note reply lands as MP3/WebM/WAV/M4A, the channel plugin transcodes to 48 kHz Ogg/Opus with
text
ffmpeg
. WhatsApp sends through Baileys with
text
ptt: true
and
text
audio/ogg; codecs=opus
. If conversion fails: Feishu falls back to attaching the original file; WhatsApp send fails rather than posting an incompatible PTT payload.
MiniMax / Xiaomi MiMo: Default MP3 (32 kHz for MiniMax
text
speech-2.8-hd
); transcoded to 48 kHz Opus for voice-note targets via
text
ffmpeg
.
Local CLI: Uses configured
text
outputFormat
. Voice-note targets are converted to Ogg/Opus and telephony output to raw 16 kHz mono PCM.
Google Gemini: Returns raw 24 kHz PCM. OpenClaw wraps as WAV for attachments, transcodes to 48 kHz Opus for voice-note targets, returns PCM directly for Talk/telephony.
Inworld: MP3 attachments, native
text
OGG_OPUS
voice-note, raw
text
PCM
22050 Hz for Talk/telephony.
xAI: MP3 by default;
text
responseFormat
may be
text
mp3|wav|pcm|mulaw|alaw
. Uses xAI's batch REST endpoint — streaming WebSocket TTS is not used. Native Opus voice-note format is not supported.
Microsoft: Uses
text
microsoft.outputFormat
(default
text
audio-24khz-48kbitrate-mono-mp3
). Telegram
text
sendVoice
accepts OGG/MP3/M4A; use OpenAI/ElevenLabs if you need guaranteed Opus voice messages. If the configured Microsoft format fails, OpenClaw retries with MP3.

OpenAI and ElevenLabs output formats are fixed per channel as listed above.

Field reference

Agent tool

The

text

tts

tool converts text to speech and returns an audio attachment for reply delivery. On Feishu, Matrix, Telegram, and WhatsApp, the audio is delivered as a voice message rather than a file attachment. Feishu and WhatsApp can transcode non-Opus TTS output on this path when

text

ffmpeg

is available.

WhatsApp sends audio through Baileys as a PTT voice note (

text

audio

with

text

ptt: true

) and sends visible text separately from PTT audio because clients do not consistently render captions on voice notes.

The tool accepts optional

text

channel

and

text

timeoutMs

fields;

text

timeoutMs

is a per-call provider request timeout in milliseconds.

Gateway RPC

Method	Purpose
text `tts.status`	Read current TTS state and last attempt.
text `tts.enable`	Set local auto preference to text `always` .
text `tts.disable`	Set local auto preference to text `off` .
text `tts.convert`	One-off text → audio.
text `tts.setProvider`	Set local provider preference.
text `tts.setPersona`	Set local persona preference.
text `tts.providers`	List configured providers and status.

OpenClaw Docs

Text-to-speech

Quick start

Pick a provider

Set the API key

Enable in config

Try it in chat

note

Supported providers

warning

Configuration

Per-agent voice overrides

Personas

Minimal persona

Full persona (provider-neutral prompt)

Persona resolution

How providers use persona prompts

Fallback policy

Model-driven directives

Slash commands

note

Per-user preferences

Output formats (fixed)

Auto-TTS behavior

Output formats by channel

Field reference

Agent tool

Gateway RPC

Service links

Related