{"record":{"id":"0b2a09ce1fb3a8ae","repo":"Comfy-Org/ComfyUI","slug":"mode-speaker-mode-uses-a-single-voice-so-aud","errorCode":null,"errorMessage":"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. Remove the @AudioN tags — the whole prompt is read in the selected voice.","messagePattern":"'(.+?)' mode uses a single voice, so @Audio(.+?) is out of range\\. Remove the @AudioN tags — the whole prompt is read in the selected voice\\.","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"comfy_api_nodes/nodes_bytedance.py","lineNumber":3190,"sourceCode":"            )\n        if max_tag > len(audio_indices):\n            raise ValueError(\n                f\"The prompt references @Audio{max_tag}, but only {len(audio_indices)} \"\n                f\"reference audio(s) are connected.\"\n            )\n    elif mode == MODE_IMAGE:\n        if not has_image:\n            raise ValueError(f\"Reference mode '{MODE_IMAGE}' requires a reference_image input.\")\n        if max_tag:\n            raise ValueError(\n                f\"@AudioN tags are not used in '{MODE_IMAGE}' mode; the prompt should contain \"\n                f\"only the text to synthesize.\"\n            )\n    elif mode == MODE_SPEAKER:\n        if not preset_voice or preset_voice not in SEED_AUDIO_VOICE_MAP:\n            raise ValueError(f\"Reference mode '{MODE_SPEAKER}' requires selecting a preset voice.\")\n        if max_tag > 1:\n            raise ValueError(\n                f\"'{MODE_SPEAKER}' mode uses a single voice, so @Audio{max_tag} is out of range. \"\n                f\"Remove the @AudioN tags — the whole prompt is read in the selected voice.\"\n            )\n    else:\n        raise ValueError(f\"Unknown reference mode: {mode!r}\")\n\n\nclass ByteDanceSeedAudioNode(IO.ComfyNode):\n\n    @classmethod\n    def define_schema(cls) -> IO.Schema:\n        return IO.Schema(\n            node_id=\"ByteDanceSeedAudio\",\n            display_name=\"ByteDance Seed Audio 1.0\",\n            category=\"partner/audio/ByteDance\",\n            description=(\n                \"Generate speech, music, sound effects and multi-speaker dialogue from a single prompt \"\n                \"with ByteDance Seed Audio 1.0. Describe the voice(s), emotion, ambience, background music \"","sourceCodeStart":3172,"sourceCodeEnd":3208,"githubUrl":"https://github.com/Comfy-Org/ComfyUI/blob/1c6d8d45b3693bfbb32385b410d813a7fd6be216/comfy_api_nodes/nodes_bytedance.py#L3172-L3208","documentation":"Thrown by the ByteDance Seed Audio node in 'preset voice' mode when the prompt contains an @AudioN tag with N > 1. Preset-voice mode uses exactly one voice for the entire prompt, so only @Audio1 (if any) is meaningful; higher indices have no corresponding audio input. The node asks you to remove the tags entirely.","triggerScenarios":"reference_mode == 'preset voice', a valid preset_voice IS selected, but max_tag parsed from the prompt is greater than 1.","commonSituations":"Dialogue prompt with <@Audio1>/<@Audio2> speaker tags reused after switching from 'audio reference' mode to 'preset voice'; template prompts that always wrap lines in speaker tags.","solutions":["Remove all @AudioN tags from the prompt; in preset voice mode the whole text is read in the selected voice.","If you genuinely need multiple distinct voices, switch reference_mode to 'audio reference' and connect one reference audio per speaker tag."],"exampleFix":"// before: prompt = \"<@Audio1>Hi<@Audio2>Hey\" (mode: preset voice)\n// after:  prompt = \"Hi. Hey.\" (mode: preset voice)","handlingStrategy":"validation","validationCode":"import re\n\ndef check_speaker_mode_prompt(prompt: str) -> None:\n    tags = [int(n) for n in re.findall(r\"@Audio(\\d+)\", prompt)]\n    if tags and max(tags) > 1:\n        raise ValueError(\"preset voice mode supports at most @Audio1; remove speaker tags\")","typeGuard":null,"tryCatchPattern":null,"preventionTips":["In preset voice mode, keep the prompt free of @AudioN tags.","Need multiple voices? Use audio reference mode with one clip per speaker."],"tags":["comfyui","bytedance","seed-audio","validation","prompt-format"],"backgroundTag":null,"analyzedSha":"1c6d8d45b3693bfbb32385b410d813a7fd6be216","analyzedAt":"2026-08-14T19:37:18.893Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}