Audio / Voice Notes (2026-01-17)

What works

• Media understanding (audio): If audio understanding is enabled (or auto‑detected), OpenClaw:
  1. Locates the first audio attachment (local path or URL) and downloads it if needed.
  2. Enforces maxBytes before sending to each model entry.
  3. Runs the first eligible model entry in order (provider or CLI).
  4. If it fails or skips (size/timeout), it tries the next entry.
  5. On success, it replaces Body with an [Audio] block and sets {{Transcript}}.
• Command parsing: When transcription succeeds, CommandBody/RawBody are set to the transcript so slash commands still work.
• Verbose logging: In --verbose, we log when transcription runs and when it replaces the body.

Auto-detection (default)

If you don’t configure models and tools.media.audio.enabled is not set to false, OpenClaw auto-detects in this order and stops at the first working option:

1. Active reply model when its provider supports audio understanding.
2. Local CLIs (if installed)
   • sherpa-onnx-offline (requires SHERPA_ONNX_MODEL_DIR with encoder/decoder/joiner/tokens)
   • whisper-cli (from whisper-cpp; uses WHISPER_CPP_MODEL or the bundled tiny model)
   • whisper (Python CLI; downloads models automatically)
3. Gemini CLI (gemini) using read_many_files
4. Provider auth
   • Configured models.providers.* entries that support audio are tried first
   • Bundled fallback order: OpenAI → Groq → xAI → Deepgram → Google → SenseAudio → ElevenLabs → Mistral

To disable auto-detection, set tools.media.audio.enabled: false. To customize, set tools.media.audio.models. Note: Binary detection is best-effort across macOS/Linux/Windows; ensure the CLI is on PATH (we expand ~), or set an explicit CLI model with a full command path.

Config examples

Provider + CLI fallback (OpenAI + Whisper CLI)

{
  tools: {
    media: {
      audio: {
        enabled: true,
        maxBytes: 20971520,
        models: [
          { provider: "openai", model: "gpt-4o-mini-transcribe" },
          {
            type: "cli",
            command: "whisper",
            args: ["--model", "base", "{{MediaPath}}"],
            timeoutSeconds: 45,
          },
        ],
      },
    },
  },
}

Provider-only with scope gating

{
  tools: {
    media: {
      audio: {
        enabled: true,
        scope: {
          default: "allow",
          rules: [{ action: "deny", match: { chatType: "group" } }],
        },
        models: [{ provider: "openai", model: "gpt-4o-mini-transcribe" }],
      },
    },
  },
}

Provider-only (Deepgram)

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "deepgram", model: "nova-3" }],
      },
    },
  },
}

Provider-only (Mistral Voxtral)

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "mistral", model: "voxtral-mini-latest" }],
      },
    },
  },
}

Provider-only (SenseAudio)

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "senseaudio", model: "senseaudio-asr-pro-1.5-260319" }],
      },
    },
  },
}

Echo transcript to chat (opt-in)

{
  tools: {
    media: {
      audio: {
        enabled: true,
        echoTranscript: true, // default is false
        echoFormat: '📝 "{transcript}"', // optional, supports {transcript}
        models: [{ provider: "openai", model: "gpt-4o-mini-transcribe" }],
      },
    },
  },
}

Notes & limits

• Provider auth follows the standard model auth order (auth profiles, env vars, models.providers.*.apiKey).
• Groq setup details: Groq.
• Deepgram picks up DEEPGRAM_API_KEY when provider: "deepgram" is used.
• Deepgram setup details: Deepgram (audio transcription).
• Mistral setup details: Mistral.
• SenseAudio picks up SENSEAUDIO_API_KEY when provider: "senseaudio" is used.
• SenseAudio setup details: SenseAudio.
• Audio providers can override baseUrl, headers, and providerOptions via tools.media.audio.
• Default size cap is 20MB (tools.media.audio.maxBytes). Oversize audio is skipped for that model and the next entry is tried.
• Tiny/empty audio files below 1024 bytes are skipped before provider/CLI transcription.
• Default maxChars for audio is unset (full transcript). Set tools.media.audio.maxChars or per-entry maxChars to trim output.
• OpenAI auto default is gpt-4o-mini-transcribe; set model: "gpt-4o-transcribe" for higher accuracy.
• Use tools.media.audio.attachments to process multiple voice notes (mode: "all" + maxAttachments).
• Transcript is available to templates as {{Transcript}}.
• tools.media.audio.echoTranscript is off by default; enable it to send transcript confirmation back to the originating chat before agent processing.
• tools.media.audio.echoFormat customizes the echo text (placeholder: {transcript}).
• CLI stdout is capped (5MB); keep CLI output concise.
• CLI args should use {{MediaPath}} for the local audio file path. Run openclaw doctor --fix to migrate deprecated {input} placeholders from older audio.transcription.command configs.

Proxy environment support

Provider-based audio transcription honors standard outbound proxy env vars:

• HTTPS_PROXY
• HTTP_PROXY
• ALL_PROXY
• https_proxy
• http_proxy
• all_proxy

If no proxy env vars are set, direct egress is used. If proxy config is malformed, OpenClaw logs a warning and falls back to direct fetch.

Mention detection in groups

When requireMention: true is set for a group chat, OpenClaw now transcribes audio before checking for mentions. This allows voice notes to be processed even when they contain mentions.

How it works:

1. If a voice message has no text body and the group requires mentions, OpenClaw performs a "preflight" transcription.
2. The transcript is checked for mention patterns (e.g., @BotName, emoji triggers).
3. If a mention is found, the message proceeds through the full reply pipeline.
4. The transcript is used for mention detection so voice notes can pass the mention gate.

Fallback behavior:

• If transcription fails during preflight (timeout, API error, etc.), the message is processed based on text-only mention detection.
• This ensures that mixed messages (text + audio) are never incorrectly dropped.

Opt-out per Telegram group/topic:

• Set channels.telegram.groups.<chatId>.disableAudioPreflight: true to skip preflight transcript mention checks for that group.
• Set channels.telegram.groups.<chatId>.topics.<threadId>.disableAudioPreflight to override per-topic (true to skip, false to force-enable).
• Default is false (preflight enabled when mention-gated conditions match).

Example: A user sends a voice note saying "Hey @Claude, what's the weather?" in a Telegram group with requireMention: true. The voice note is transcribed, the mention is detected, and the agent replies.

Gotchas

• Scope rules use first-match wins. chatType is normalized to direct, group, or room.
• Ensure your CLI exits 0 and prints plain text; JSON needs to be massaged via jq -r .text.
• For parakeet-mlx, if you pass --output-dir, OpenClaw reads <output-dir>/<media-basename>.txt when --output-format is txt (or omitted); non-txt output formats fall back to stdout parsing.
• Keep timeouts reasonable (timeoutSeconds, default 60s) to avoid blocking the reply queue.
• Preflight transcription only processes the first audio attachment for mention detection. Additional audio is processed during the main media understanding phase.

Related

• Media understanding
• Talk mode
• Voice wake