{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","arxiv_id":"2412.02612","date":"2024-12-03","proceeding":null,"authors":["Aohan Zeng","Zhengxiao Du","Mingdao Liu","Kedong Wang","Shengmin Jiang","Lei Zhao","Yuxiao Dong","Jie Tang"],"abstract":"We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It supports both Chinese and English, engages in real-time voice conversations, and varies vocal nuances such as emotion, intonation, speech rate, and dialect according to user instructions. GLM-4-Voice uses an ultra-low bitrate (175bps), single-codebook speech tokenizer with 12.5Hz frame rate derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. To efficiently transfer knowledge from text to speech modalities, we synthesize speech-text interleaved data from existing text pre-training corpora using a text-to-token model. We continue pre-training from the pre-trained text language model GLM-4-9B with a combination of unsupervised speech data, interleaved speech-text data, and supervised speech-text data, scaling up to 1 trillion tokens, achieving state-of-the-art performance in both speech language modeling and spoken question answering. We then fine-tune the pre-trained model with high-quality conversational speech data, achieving superior performance compared to existing baselines in both conversational ability and speech quality. The open models can be accessed through https://github.com/THUDM/GLM-4-Voice and https://huggingface.co/THUDM/glm-4-voice-9b.","url_abs":"https://arxiv.org/abs/2412.02612v1","url_pdf":"https://arxiv.org/pdf/2412.02612v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"glm-4-voice-towards-intelligent-and-human","repo_url":"https://github.com/thudm/glm-4-voice","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"chatbot","task_name":"Chatbot"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.02612","atlas_url":"https://app.syntology.ai/?focus=2412.02612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02612"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/glm-4-voice","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ace1f28a134f74ed","entry":"fade_in_out","repo":"thudm/glm-4-voice","repo_kind":"official","path":"flow_inference.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/flow_inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ace1f28a134f74ed"}},{"code_sha256_prefix":"d1667366e1daf29d","entry":"load_quantize_encoder","repo":"thudm/glm-4-voice","repo_kind":"official","path":"speech_tokenizer/utils.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/speech_tokenizer/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d1667366e1daf29d"}},{"code_sha256_prefix":"410b17047bc4072e","entry":"mse_loss_with_mask","repo":"thudm/glm-4-voice","repo_kind":"official","path":"speech_tokenizer/modeling_whisper.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/speech_tokenizer/modeling_whisper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"410b17047bc4072e"}},{"code_sha256_prefix":"04714b15c8ffaf40","entry":"sinusoids","repo":"thudm/glm-4-voice","repo_kind":"official","path":"speech_tokenizer/modeling_whisper.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/speech_tokenizer/modeling_whisper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04714b15c8ffaf40"}},{"code_sha256_prefix":"2d27b1b6ddc05cb6","entry":"vector_quantize","repo":"thudm/glm-4-voice","repo_kind":"official","path":"speech_tokenizer/modeling_whisper.py","file_url":"https://github.com/thudm/glm-4-voice/blob/HEAD/speech_tokenizer/modeling_whisper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d27b1b6ddc05cb6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}