Skip to main content
Azure Speech is a bundled Azure AI Speech text-to-speech provider. OpenClaw calls the Azure Speech REST API directly with SSML, synthesizing MP3 for standard replies, native Ogg/Opus for voice notes, and 8 kHz mulaw for telephony channels such as Voice Call. The request sends the provider-owned output format through the X-Microsoft-OutputFormat header.
DetailValue
Provider IDazure-speech (alias: azure)
WebsiteAzure AI Speech
DocsSpeech REST text-to-speech
AuthAZURE_SPEECH_KEY plus AZURE_SPEECH_REGION
Default voiceen-US-JennyNeural
Default file outputaudio-24khz-48kbitrate-mono-mp3
Default voice-note fileogg-24khz-16bit-mono-opus

​
Getting started

1

Create an Azure Speech resource

In the Azure portal, create a Speech resource. Copy KEY 1 from Resource Management > Keys and Endpoint, and copy the resource location such as eastus.
AZURE_SPEECH_KEY=<speech-resource-key>
AZURE_SPEECH_REGION=eastus
2

Select Azure Speech in messages.tts

{
  messages: {
    tts: {
      auto: "always",
      provider: "azure-speech",
      providers: {
        "azure-speech": {
          voice: "en-US-JennyNeural",
          lang: "en-US",
        },
      },
    },
  },
}
3

Send a message

Send a reply through any connected channel. OpenClaw synthesizes the audio with Azure Speech and delivers MP3 for standard audio, or Ogg/Opus when the channel expects a voice note.

​
Configuration options

All options live under messages.tts.providers["azure-speech"].
OptionDescription
apiKeyAzure Speech resource key. Falls back to AZURE_SPEECH_KEY, AZURE_SPEECH_API_KEY, or SPEECH_KEY.
regionAzure Speech resource region. Falls back to AZURE_SPEECH_REGION or SPEECH_REGION.
endpointOptional Azure Speech endpoint override. Falls back to AZURE_SPEECH_ENDPOINT.
baseUrlOptional Azure Speech base URL override.
voiceAzure voice ShortName (default en-US-JennyNeural). Legacy alias: voiceId.
langSSML language code (default en-US).
outputFormatAudio-file output format (default audio-24khz-48kbitrate-mono-mp3).
voiceNoteOutputFormatVoice-note output format (default ogg-24khz-16bit-mono-opus).
timeoutMsRequest timeout override in milliseconds. Falls back to the global messages.tts.timeoutMs.
The provider is considered configured once apiKey is set plus one of region, endpoint, or baseUrl. Env vars are only checked as a fallback for config keys left unset.

​
Notes

Azure Speech uses a Speech resource key, not an Azure OpenAI key. The key is sent as Ocp-Apim-Subscription-Key; OpenClaw derives https://<region>.tts.speech.microsoft.com from region unless you provide endpoint or baseUrl.
Use the Azure Speech voice ShortName value, for example en-US-JennyNeural. The bundled provider can list voices through the same Speech resource and filters out voices marked deprecated, retired, or disabled.
Azure accepts output formats such as audio-24khz-48kbitrate-mono-mp3, ogg-24khz-16bit-mono-opus, and riff-24khz-16bit-mono-pcm. OpenClaw requests Ogg/Opus for voice-note targets so channels can send native voice bubbles without an extra MP3 conversion, and forces raw-8khz-8bit-mono-mulaw for telephony targets.
azure is accepted as a provider alias for existing config, but new config should use azure-speech to avoid confusion with Azure OpenAI model providers.

Text-to-speech

TTS overview, providers, and messages.tts config.

Configuration

Full config reference including messages.tts settings.

Providers

All bundled OpenClaw providers.

Troubleshooting

Common issues and debugging steps.