Volcengine (Doubao)

The Volcengine provider gives access to Doubao models and third-party models hosted on Volcano Engine, with separate endpoints for general and coding workloads. The same bundled plugin can also register Volcengine Speech as a TTS provider.

Getting started

1. Set the API key

   Run interactive onboarding:

   openclaw onboard --auth-choice volcengine-api-key
   

   This registers both the general (volcengine) and coding (volcengine-plan) providers from a single API key.

2. Set a default model

   {
     agents: {
       defaults: {
         model: { primary: "volcengine-plan/ark-code-latest" },
       },
     },
   }
   

3. Verify the model is available

   openclaw models list --provider volcengine
   openclaw models list --provider volcengine-plan
   

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice volcengine-api-key \
  --volcengine-api-key "$VOLCANO_ENGINE_API_KEY"

Providers and endpoints

Built-in catalog

Text-to-speech

Volcengine TTS uses the BytePlus Seed Speech HTTP API and is configured separately from the OpenAI-compatible Doubao model API key. In the BytePlus console, open Seed Speech > Settings > API Keys and copy the API key, then set:

export VOLCENGINE_TTS_API_KEY="byteplus_seed_speech_api_key"
export VOLCENGINE_TTS_RESOURCE_ID="seed-tts-1.0"

Then enable it in openclaw.json:

{
  messages: {
    tts: {
      auto: "always",
      provider: "volcengine",
      providers: {
        volcengine: {
          apiKey: "byteplus_seed_speech_api_key",
          voice: "en_female_anna_mars_bigtts",
          speedRatio: 1.0,
        },
      },
    },
  },
}

For voice-note targets, OpenClaw asks Volcengine for provider-native ogg_opus. For normal audio attachments, it asks for mp3. Provider aliases bytedance and doubao also resolve to the same speech provider.

The default resource id is seed-tts-1.0 because that is what BytePlus grants to newly created Seed Speech API keys in the default project. If your project has TTS 2.0 entitlement, set VOLCENGINE_TTS_RESOURCE_ID=seed-tts-2.0.

Legacy AppID/token auth remains supported for older Speech Console applications:

export VOLCENGINE_TTS_APPID="speech_app_id"
export VOLCENGINE_TTS_TOKEN="speech_access_token"
export VOLCENGINE_TTS_CLUSTER="volcano_tts"

Advanced configuration

Related