calesthio/OpenMontage · error · ValueError

text exceeds Kling TTS safety limit of 5000 characters

Error message

text exceeds Kling TTS safety limit of 5000 characters

What it means

Raised by kling_tts._build_request when the stripped text exceeds 5000 characters — Kling's official TTS API hard limit. The wrapper enforces it client-side to avoid a wasted round trip and an opaque upstream rejection.

Source

Thrown at tools/audio/kling_tts.py:199

                "format": paths[0].suffix.lstrip(".") or "mp3",
                "audio_duration_seconds": round(audio_duration, 2) if audio_duration else None,
                "cost_estimate_confidence": "low",
                "cost_estimate_basis": "Conservative estimate pending official account-usage reconciliation.",
                **self._account_usage_result(inputs, client),
                **self._callback_result_data(inputs, task_id),
            },
            artifacts=[str(path) for path in paths],
            cost_usd=self.estimate_cost(inputs),
            duration_seconds=round(time.time() - start, 2),
            model="kling-official-tts",
        )

    def _build_request(self, inputs: dict[str, Any]) -> dict[str, Any]:
        text = str(inputs.get("text") or "").strip()
        if not text:
            raise ValueError("text is required")
        if len(text) > 5000:
            raise ValueError("text exceeds Kling TTS safety limit of 5000 characters")

        voice_id = str(inputs.get("voice_id") or "").strip()
        if not voice_id:
            raise ValueError("voice_id is required for Kling official TTS")

        voice_language = str(inputs.get("voice_language") or "en")
        if voice_language not in TTS_LANGUAGES:
            raise ValueError(f"voice_language must be one of: {', '.join(TTS_LANGUAGES)}")

        voice_speed = float(inputs.get("voice_speed", 1.0))
        if voice_speed < TTS_SPEED_MIN or voice_speed > TTS_SPEED_MAX:
            raise ValueError(f"voice_speed must be between {TTS_SPEED_MIN} and {TTS_SPEED_MAX}")

        payload: dict[str, Any] = {
            "text": text,
            "voice_id": voice_id,
            "voice_language": voice_language,
            "voice_speed": voice_speed,

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Split text into chunks under 5000 characters at sentence boundaries and make sequential calls
2. Use the numbered output path support (numbered_output_path) to keep chunk artifacts ordered
3. Compute len(text.strip()) before calling and warn in the pipeline

Example fix

// before
result = tool.execute({"text": long_script, "voice_id": vid})  # raises if >5000

// after
chunks = [long_script[i:i+4800] for i in range(0, len(long_script), 4800)]
results = [tool.execute({"text": c, "voice_id": vid}) for c in chunks]

text = str(inputs.get("text") or "").strip()
if len(text) > 5000:
    raise ValueError(f"text is {len(text)} chars; split into <=5000-char chunks")

When it happens

Trigger: Long narration scripts, full articles, or concatenated segments passed as a single text value longer than 5000 chars.

Common situations: Feeding an entire blog post or voiceover script to one TTS call; merging multiple scenes into one request; CJK text where character count hits the cap faster than expected.

Related errors

• text is required
• voice_id is required for Kling official TTS
• voice_language must be one of: {', '.join(TTS_LANGUAGES)}
• voice_speed must be between {TTS_SPEED_MIN} and {TTS_SPEED_M
• element_list must be a list of element ids or objects

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/db3262f257f700de. Report an issue: GitHub.