TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context

• URL: http://arxiv.org/abs/2609.08703v1
• Date: Tue, 08 Sep 2026 13:03:46 GMT
• Title: TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context
• Abstract summary: TontaubeV1 is a model that preserves natural prosody while enabling streaming from a single consumer GPU.<n>Our design assumes that prosodic structure is largely established when the semantic stream is generated.<n>The model accepts up to one minute of reference audio for voice conditioning and is designed primarily for English and German.
• Score: 0.04583541422554719
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-speech systems often face a trade-off between natural prosody and efficient inference: higher perceptual quality typically comes at increased computational cost and latency. We present TontaubeV1, a model that preserves natural prosody while enabling streaming from a single consumer GPU. Speech is encoded by the hierarchical DualCodec representation at 12.5 Hz, which separates a semantic stream from successive acoustic refinements. Our design assumes that prosodic structure is largely established when the semantic stream is generated, and allocates capacity accordingly: a Qwen3-1.7B-derived transformer predicts that stream and thereby the utterance duration, while three progressively smaller Qwen3-0.6B-derived transformers each add one acoustic refinement. Text is tokenized per character rather than by subword. Paired text and audio markers at shared positions support long-form generation with bounded context, and overlapping DualCodec reconstructions are mapped into the VibeVoice acoustic latent space and decoded causally, enabling streaming despite DualCodec's noncausal decoder. The model accepts up to one minute of reference audio for voice conditioning and is designed primarily for English and German, with additional multilingual support. The four predictors total 2.9B parameters; on a single RTX 5090 the streaming path reaches approximately 200 ms to first audio. In separate non-streaming measurements, the end-to-end real-time factor (RTF) is 0.08 for one input and the aggregate RTF is 0.02 across eight concurrent inputs. On our LLM-as-a-judge audiobook-reading benchmark, TontaubeV1 matches ElevenLabs Flash v2.5 and outperforms Fish Audio S2 Pro, the April 2026 Gradium API, and Cartesia Sonic 3 on prosody. The model weights are released on Hugging Face under the Tontaube Community Model License 1.0.

Related papers

• Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers [11.102698205402675]
  Siri Expressive Voices synthesizes rich, conversational speech in real time and entirely on device.<n>A detokenizer converts semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX)<n>A single reusable depth decoder with Diffusion Transformer (DiT)-style stage conditioning generates all RVQ levels autoregressively, replacing the dedicated per-level decoders of prior multi-decoder architectures.
  arXiv  Detail & Related papers  (2026-07-26T19:20:01Z)
• FreyaTTS Technical Report [0.0]
  We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speaker model.<n>It operates in the frozen continuous latent space of AudioVAE2 (16 kHz encode, 48 kHz decode), allowing the model to focus its capacity on text-to-latent mapping.<n>It achieves a band-matched word error rate (WER) of 8.0% and character error rate (CER) of 3.0%, outperforming substantially larger open-source systems.
  arXiv  Detail & Related papers  (2026-07-10T15:36:30Z)
• Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models [68.51256516936338]
  Wan-Streamer is an end-to-end native interactive foundation model for low-streaming interaction.<n>It seamlessly models audio and video as both input and output within single Transformer sequence.<n>It achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency.
  arXiv  Detail & Related papers  (2026-06-23T18:01:03Z)
• Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model [52.79436545460808]
  We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation.<n>DaVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer.<n>It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French.
  arXiv  Detail & Related papers  (2026-03-23T13:49:06Z)
• Voxtral Realtime [134.66962524291424]
  Voxtral Realtime is a streaming automatic speech recognition model.<n>It matches offline transcription quality at sub-second latency.<n>We release the model weights under the Apache 2.0 license.
  arXiv  Detail & Related papers  (2026-02-11T19:17:10Z)
• Qwen3-TTS Technical Report [64.94647392030824]
  We present the Qwen3-TTS series, a family of advanced multilingual, controllable, robust, and streaming text-to-speech models.<n>Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.<n>Qwen3-TTS adopts a dual-track LM architecture for real-time synthesis, coupled with two speech tokenizers.
  arXiv  Detail & Related papers  (2026-01-22T03:51:43Z)
• Qwen3-Omni Technical Report [105.11829337290249]
  We present Qwen3- Omni, a single multimodal model that maintains state-of-the-art performance across text, image, audio, and video.<n>Qwen3- Omni matches the performance of same-sized single-modal models within the Qwen series and excels particularly on audio tasks.<n>It supports text interaction in 119 languages, speech understanding in 19 languages, and speech generation in 10 languages.
  arXiv  Detail & Related papers  (2025-09-22T13:26:24Z)
• TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling [13.05578634768109]
  We introduce the Text-aware Diffusion Transformer Speech Codec (TaDiCodec)<n>TaDiCodec employs end-to-end optimization for quantization and reconstruction through a diffusion autoencoder.<n>It achieves an extremely low frame rate of 6.25 Hz and corresponding compression of 0.0875 kbps with a single-layer codebook for 24 kHz speech.
  arXiv  Detail & Related papers  (2025-08-22T20:45:03Z)
• FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis [77.06890315052563]
  We propose FastLTS, a non-autoregressive end-to-end model which can directly synthesize high-quality speech audios from unconstrained talking videos with low latency. Experiments show that our model achieves $19.76times$ speedup for audio generation compared with the current autoregressive model on input sequences of 3 seconds.
  arXiv  Detail & Related papers  (2022-07-08T10:10:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.