### Changes

- Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.6.3. Thanks @vincentkoc.

- TTS/agents: allow `agents.list[].tts` to override global

`messages.tts` for per-agent voices while keeping shared provider

credentials and preferences in the existing TTS config surface.

- Providers/Azure Speech: add Azure Speech as a bundled TTS provider with

Speech-resource auth, voice listing, SSML escaping, native Ogg/Opus

voice-note output, and telephony output. (#51776) Thanks @leonchui.

211e9d4cdb309e7fe0c1ed91d060201240a9287f8c5cb3c893aba3f904a20d30 config-baseline.json

ffda2d2911adc03148a368f3b40b17cbdcb7af0066bccdc555e8d596cdea8cda config-baseline.core.json

3efb041739877bd5387ffc87e0ddd11be43d80d38e7779407ce8091dcb797e5e config-baseline.json

5c6e35c5846f654d717d4b20853649e0b45a746423834f539b2a2223abcd5226 config-baseline.core.json

7cd9c908f066c143eab2a201efbc9640f483ab28bba92ddeca1d18cc2b528bc3 config-baseline.channel.json

9e131d7734f8b9cc9e7f8af6cc6b6dc81c9971dc551fadbe66fb0d682173f32d config-baseline.plugin.json

a5479c182ec987bb21e814b8a4e7b3bda7190ae5c2b35fd5ca403dfa48afa115 config-baseline.plugin.json

c911117176b41eebf26470618274a7e093910e9b36855bc045bc8a92f6856745 plugin-sdk-api-baseline.json

ff360635f95beb217b9dd207a87eaf331319a7671aea03acfe05911756741b21 plugin-sdk-api-baseline.jsonl

6eb33044c2a4726f1aeb2d18052643c38c8bf5244bb970f969b1583365063e8b plugin-sdk-api-baseline.json

06e70516047f98d78963c238f1671feb3eea7c7e559c6fa84f403b9562028bb2 plugin-sdk-api-baseline.jsonl

fastModeDefault: false, // per-agent fast mode override

embeddedHarness: { runtime: "auto", fallback: "pi" },

params: { cacheRetention: "none" }, // overrides matching defaults.models params by key

tts: {

providers: {

elevenlabs: { voiceId: "EXAVITQu4vr4xnSDxMaL" },

},

},

skills: ["docs-search"], // replaces agents.defaults.skills when set

identity: {

name: "Samantha",

- `default`: when multiple are set, first wins (warning logged). If none set, first list entry is default.

- `model`: string form overrides `primary` only; object form `{ primary, fallbacks }` overrides both (`[]` disables global fallbacks). Cron jobs that only override `primary` still inherit default fallbacks unless you set `fallbacks: []`.

- `params`: per-agent stream params merged over the selected model entry in `agents.defaults.models`. Use this for agent-specific overrides like `cacheRetention`, `temperature`, or `maxTokens` without duplicating the whole model catalog.

- `tts`: optional per-agent text-to-speech overrides. The block deep-merges over `messages.tts`, so keep shared provider credentials and fallback policy in `messages.tts` and set only persona-specific values such as provider, voice, model, style, or auto mode here.

- `skills`: optional per-agent skill allowlist. If omitted, the agent inherits `agents.defaults.skills` when set; an explicit list replaces defaults instead of merging, and `[]` means no skills.

- `thinkingDefault`: optional per-agent default thinking level (`off | minimal | low | medium | high | xhigh | adaptive | max`). Overrides `agents.defaults.thinkingDefault` for this agent when no per-message or session override is set. The selected provider/model profile controls which values are valid; for Google Gemini, `adaptive` keeps provider-owned dynamic thinking (`thinkingLevel` omitted on Gemini 3/3.1, `thinkingBudget: -1` on Gemini 2.5).

- `reasoningDefault`: optional per-agent default reasoning visibility (`on | off | stream`). Applies when no per-message or session reasoning override is set.

- `models.providers.*.request.tls.passphrase`

- `skills.entries.*.apiKey`

- `agents.defaults.memorySearch.remote.apiKey`

- `agents.list[].tts.providers.*.apiKey`

- `agents.list[].memorySearch.remote.apiKey`

- `talk.providers.*.apiKey`

- `messages.tts.providers.*.apiKey`

"secretShape": "secret_input",

"optIn": true

},

{

"id": "agents.list[].tts.providers.*.apiKey",

"configFile": "openclaw.json",

"path": "agents.list[].tts.providers.*.apiKey",

"secretShape": "secret_input",

"optIn": true

},

{

"id": "auth-profiles.api_key.key",

"configFile": "auth-profiles.json",

}

```

### Per-agent voice overrides

Use `agents.list[].tts` when one agent should speak with a different provider,

voice, model, style, or auto-TTS mode. The agent block deep-merges over

`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",

},

},

},

},

],

},

}

```

Precedence for automatic replies is:

1. `messages.tts`

2. active `agents.list[].tts`

3. local `/tts` preferences for this host

4. inline `[[tts:...]]` directives when model overrides are enabled

### OpenAI primary with ElevenLabs fallback

```json5

- `maxLength` (summary threshold; default 1500 chars)

- `summarize` (default `true`)

These override `messages.tts.*` for that host.

These override the effective config from `messages.tts` plus the active

`agents.list[].tts` block for that host.

## Output formats (fixed)

};

});

const { _test, maybeApplyTtsToPayload } = await import("./tts.js");

const { _test, maybeApplyTtsToPayload, resolveTtsConfig } = await import("./tts.js");

const nativeVoiceNoteChannels = ["discord", "feishu", "matrix", "telegram", "whatsapp"] as const;

});

});

});

describe("speech-core per-agent TTS config", () => {

it("deep-merges the active agent TTS override over messages.tts", () => {

const cfg = {

messages: {

tts: {

enabled: true,

provider: "openai",

providers: {

openai: {

apiKey: "${OPENAI_API_KEY}",

voice: "coral",

speed: 1,

},

},

},

},

agents: {

list: [

{

id: "reader",

tts: {

provider: "openai",

providers: {

openai: {

voice: "nova",

},

},

},

},

],

},

} satisfies OpenClawConfig;

const resolved = resolveTtsConfig(cfg, "reader");

expect(resolved.rawConfig).toMatchObject({

enabled: true,

provider: "openai",

providers: {

openai: {

apiKey: "${OPENAI_API_KEY}",

voice: "nova",

speed: 1,

},

},

});

});

it("ignores prototype-pollution keys in agent TTS overrides", () => {

const cfg = {

messages: {

tts: {

provider: "openai",

providers: {

openai: {

voice: "coral",

},

},

},

},

agents: {

list: [

{

id: "reader",

tts: JSON.parse(

'{"providers":{"openai":{"voice":"nova","__proto__":{"polluted":true}}}}',

),

},

],

},

} as OpenClawConfig;

const resolved = resolveTtsConfig(cfg, "reader");

expect(resolved.rawConfig?.providers?.openai).toEqual({ voice: "nova" });

expect(({} as Record<string, unknown>).polluted).toBeUndefined();

});

});