Hmbown/CodeWhale · error · anyhow::Error

mimo-v2.5-tts-voicedesign requires --voice-prompt or --instr

Error message

mimo-v2.5-tts-voicedesign requires --voice-prompt or --instruction to describe the voice

What it means

Voice-design guard: when the resolved model contains "voicedesign" (mimo-v2.5-tts-voicedesign), the command needs a natural-language description of the voice supplied via `--voice-prompt` or `--instruction` (combined by combine_speech_instructions). Without one the design model has nothing to synthesize a voice from, so the CLI bails.

Source

Thrown at crates/tui/src/lib.rs:7392

        voice_prompt.is_some(),
    );
    let model_lower = model.to_ascii_lowercase();
    if !model_lower.contains("tts") {
        bail!(
            "speech requires a TTS model (examples: {}); got {model}",
            SPEECH_MODEL_EXAMPLES.join(", ")
        );
    }
    let is_voice_design = model_lower.contains("voicedesign");
    let is_voice_clone = model_lower.contains("voiceclone");

    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)")
    })?;

View on GitHub (pinned to 0c42157ee5)

Solutions

Add `--voice-prompt "..."` describing the target voice (tone, gender, pace)
Or add `--instruction "..."`; when both are present they are merged
If you did not want voice design, switch the model back to mimo-v2.5-tts

Example fix

// before
$ codewhale speech --model mimo-v2.5-tts-voicedesign
Error: mimo-v2.5-tts-voicedesign requires --voice-prompt or --instruction to describe the voice

// after
$ codewhale speech --model mimo-v2.5-tts-voicedesign --voice-prompt 'calm male narrator, slow pace'

Defensive patterns

Strategy: validation

Validate before calling

case "$MODEL" in *voicedesign*)
  [ -n "${VOICE_PROMPT}${INSTRUCTION}" ] || { echo 'voicedesign needs --voice-prompt or --instruction' >&2; exit 2; } ;;
esac

Prevention

Treat a voice description as mandatory input wherever the design model is used
Keep prompts in variables so the flag is never accidentally dropped

When it happens

Trigger: `codewhale speech --model mimo-v2.5-tts-voicedesign` (or inference selecting it via --voice-prompt) with neither `--voice-prompt` nor `--instruction`, or both blank after trimming.

Common situations: Switching from plain TTS to voice design and assuming a default voice applies; passing --instruction containing only whitespace.

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

AI-assisted analysis of Hmbown/CodeWhale@0c42157ee5 (2026-08-20). Data as JSON: /api/errors/619d47c1b6f3c182. Report an issue: GitHub.