Hmbown/CodeWhale · error · anyhow::Error

mimo-v2.5-tts-voiceclone requires --clone-voice <mp3|wav> or

Error message

mimo-v2.5-tts-voiceclone requires --clone-voice <mp3|wav> or --voice <data-uri>

What it means

Voice-clone guard: for model names containing "voiceclone" the request must carry a voice sample — either `--clone-voice <path to mp3/wav>` (base64-encoded to a data URI, 10 MiB cap) or `--voice` holding an existing data:audio/... data-URI. With neither present the clone model cannot operate, so the CLI bails instead of sending a doomed request.

Source

Thrown at crates/tui/src/lib.rs:7404

    let instruction = combine_speech_instructions(instruction, voice_prompt);
    if is_voice_design
        && instruction
            .as_deref()
            .is_none_or(|value| value.trim().is_empty())
    {
        bail!(
            "mimo-v2.5-tts-voicedesign requires --voice-prompt or --instruction to describe the voice"
        );
    }

    let voice = if let Some(clone_path) = clone_voice {
        Some(encode_voice_clone_sample_data_uri(&clone_path)?)
    } else if is_voice_design {
        None
    } else if let Some(value) = voice.filter(|value| !value.trim().is_empty()) {
        Some(value)
    } else if is_voice_clone {
        bail!("mimo-v2.5-tts-voiceclone requires --clone-voice <mp3|wav> or --voice <data-uri>");
    } else {
        Some(DEFAULT_VOICE.to_string())
    };
    let format = normalize_speech_format(&format).with_context(|| {
        format!("Unsupported speech format '{format}' (allowed: wav, mp3, pcm16)")
    })?;
    let output = output.unwrap_or_else(|| {
        output_dir
            .or_else(|| config.speech_output_dir())
            .unwrap_or_default()
            .join(default_speech_output_name(&format))
    });

    let client = DeepSeekClient::new(config)?;
    let response = client
        .synthesize_speech(SpeechSynthesisRequest {
            model: model.clone(),
            text,

View on GitHub (pinned to 0c42157ee5)

Solutions

1. Clone from a file: add `--clone-voice <path>` to an mp3 or wav sample
2. Or supply the sample inline: `--voice data:audio/wav;base64,...`
3. If you meant ordinary TTS, use the non-clone model (mimo-v2.5-tts) with the default voice

Example fix

// before
$ codewhale speech --model mimo-v2.5-tts-voiceclone
Error: mimo-v2.5-tts-voiceclone requires --clone-voice <mp3|wav> or --voice <data-uri>

// after
$ codewhale speech --model mimo-v2.5-tts-voiceclone --clone-voice sample.wav
// or: --voice data:audio/wav;base64,...

case "$MODEL" in *voiceclone*)
  [ -n "${CLONE_VOICE}${VOICE}" ] || { echo 'voiceclone needs --clone-voice or --voice' >&2; exit 2; } ;;
esac

When it happens

Trigger: `codewhale speech --model mimo-v2.5-tts-voiceclone` where `--clone-voice` is absent and `--voice` is absent or whitespace-only (a non-blank --voice value is passed through to the API instead).

Common situations: Forgetting the sample file after switching models; running voiceclone with only a text prompt; assuming a named default voice suffices for cloning.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• Use either --clone-voice or --voice for cloned voice data, n
• mimo-v2.5-tts-voicedesign requires --voice-prompt or --instr
• speech synthesis requires provider 'xiaomi-mimo' (current: {
• `speech` requires provider = "xiaomi-mimo" (current: {}). Ru
• speech requires a TTS model (examples: {}); got {model}

AI-assisted analysis of Hmbown/CodeWhale@0c42157ee5 (2026-08-20). Data as JSON: /api/errors/679877ada8930b7a. Report an issue: GitHub.