AI News AI资讯 3d ago Updated 3d ago 更新于 3天前 46

Cartesia Ships Sonic-3.6: A Streaming TTS Model That Now Leads Both Artificial Analysis Speech Arenas Cartesia发布Sonic-3.6:一款在Artificial Analysis双语音榜单登顶的流式TTS模型

Cartesia released Sonic-3.6, a real-time streaming text-to-speech model that now ranks #1 on both Artificial Analysis speech leaderboards (1,283 Elo Provider Voice, 1,123 Elo Controlled Voice) The model uses state space models instead of transformers, achieving sub-90ms time-to-first-audio latency Sonic-3.6's top ranking on the Controlled Voice board indicates genuine synthesis engine improvement rather than just a larger voice catalog Available in beta as a hosted API only; no self-hosted weigh Cartesia发布Sonic-3.6流式TTS模型,在Artificial Analysis双榜单(Provider Voice 1,283 Elo、Controlled Voice 1,123 Elo)均位列第一 采用状态空间模型(State Space Models)架构替代Transformer,实现亚90毫秒首音频延迟,突破速度与自然度的传统权衡 Controlled Voice榜单领先证明引擎本身改进,而非仅依赖声音库优势,技术含金量更高 闭源商业模型,仅提供托管API(无自托管权重),定价$49/百万字符,为ElevenLabs同等级产品的一半 生产级功能包括:10秒即时声音克隆

68
Hot 热度
65
Quality 质量
62
Impact 影响力

Analysis 深度分析

TL;DR

  • Cartesia released Sonic-3.6, a real-time streaming text-to-speech model that now ranks #1 on both Artificial Analysis speech leaderboards (1,283 Elo Provider Voice, 1,123 Elo Controlled Voice)
  • The model uses state space models instead of transformers, achieving sub-90ms time-to-first-audio latency
  • Sonic-3.6's top ranking on the Controlled Voice board indicates genuine synthesis engine improvement rather than just a larger voice catalog
  • Available in beta as a hosted API only; no self-hosted weights or open-source release
  • Pricing at $49 per 1M characters (per Artificial Analysis), half the cost of ElevenLabs Eleven v3, with production-focused features like inline expression tags, instant voice cloning from ~10 seconds, and native alphanumerics handling

Why It Matters

Sonic-3.6 represents a significant milestone in real-time TTS by demonstrating that state space models can outperform transformer-based architectures on both naturalness and latency benchmarks, challenging the industry assumption that these tradeoffs are inevitable. For AI practitioners building voice agents, the model's production-ready features—inline expression tags, instant voice cloning, and sub-90ms TTFA—make it immediately deployable for conversational AI applications without extensive preprocessing. The Controlled Voice leaderboard victory is particularly noteworthy because it isolates engine quality from voice catalog breadth, providing a more rigorous measure of genuine model improvement.

Technical Details

  • Architecture: Sonic-3.6 runs on state space models (SSMs) rather than transformers, which Cartesia frames as resolving the traditional speed-versus-naturalness tradeoff through architectural innovation rather than incremental scaling
  • Latency: Vendor-stated sub-90ms time-to-first-audio (TTFA) for TTS and 100ms transcript latency for the companion Ink-2 speech-to-text model; these are model-level latencies, not end-to-end round-trip measurements
  • Benchmarks: #1 on both Artificial Analysis speech leaderboards—1,283 Elo on Provider Voice (where each model uses its own voices) and 1,123 Elo on Controlled Voice (where all models are cloned onto the same eight reference voices, isolating synthesis engine quality)
  • Production Features: Inline expression tags (e.g., [laughter]), instant voice cloning from ~10 seconds of audio, custom pronunciation dictionaries with IPA overrides, exposed speed/volume/emotion parameters via API, LiveKit Agents plugin integration, and native handling of alphanumerics without preprocessing
  • Deployment: Hosted API only in beta; no self-hosted weights or Hugging Face repository; Sonic 3.5 remains the stable version in partner ecosystems

Industry Insight

  • The rise of state space models in production TTS signals a potential architectural shift away from transformers for latency-sensitive audio generation tasks; practitioners should evaluate SSM-based models for real-time voice agent deployments where sub-100ms TTFA is critical
  • Sonic-3.6's Controlled Voice leaderboard dominance suggests the next competitive frontier in TTS is synthesis engine quality rather than voice catalog size, pushing vendors to invest in fundamental model architecture improvements over data collection
  • The pricing landscape ($49/M characters for Sonic-3.6 vs. $100/M for ElevenLabs vs. $10/M for Speechify Simba 3.2 at lower Elo) indicates a mid-tier value opportunity; teams should benchmark actual round-trip latency and quality in their specific deployment context rather than relying on vendor-stated model latency figures

TL;DR

  • Cartesia发布Sonic-3.6流式TTS模型,在Artificial Analysis双榜单(Provider Voice 1,283 Elo、Controlled Voice 1,123 Elo)均位列第一
  • 采用状态空间模型(State Space Models)架构替代Transformer,实现亚90毫秒首音频延迟,突破速度与自然度的传统权衡
  • Controlled Voice榜单领先证明引擎本身改进,而非仅依赖声音库优势,技术含金量更高
  • 闭源商业模型,仅提供托管API(无自托管权重),定价$49/百万字符,为ElevenLabs同等级产品的一半
  • 生产级功能包括:10秒即时声音克隆、内联表情标签、IPA发音覆盖、原生字母数字处理、多语言代码切换(如Hinglish)

为什么值得看

Sonic-3.6在Controlled Voice榜单的领先具有技术评估意义——该榜单将所有模型克隆到相同八种参考声音,隔离了合成引擎与声音库的差异,证明其核心架构进步。状态空间模型在实时TTS领域的成功应用,为低延迟高自然度语音合成提供了新的技术范式,对AI语音代理和实时交互应用具有重要参考价值。

技术解析

  • 架构创新:采用状态空间模型(SSM)而非Transformer,Cartesia将延迟、自然度、准确率、成本的传统权衡重新定义为架构问题而非必然约束,实现亚90ms TTFA(首音频延迟)和100ms转录延迟(Ink-2 STT模型)
  • 性能基准:Artificial Analysis双榜第一,Provider Voice 1,283 Elo、Controlled Voice 1,123 Elo;后者第二名为Sonic-3.5,第三名为ElevenLabs Eleven v3,形成代际领先
  • 生产功能:支持内联表情标签(如[laughter])、10秒即时声音克隆、自定义发音词典(含IPA覆盖如<<s|ə|ˈ|p|i|n|ə>>)、API级速度/音量/情感参数控制、LiveKit Agents插件集成、原生字母数字处理无需预处理
  • 部署与定价:仅Beta托管API可用(文档仍列3.5为稳定版),无开源权重;定价$49/百万字符(Speechify Simba 3.2仅$10但Elo 1,240),Scale套餐$299/月含约10,667分钟TTS和15并发,语音代理另计$0.06/分钟
  • 语言支持:演示展示英语自然停顿和填充词,以及印英混合代码切换(Hinglish),支持多语言本地化场景

行业启示

  • 架构演进信号:状态空间模型在实时TTS的成功验证,预示其可能成为下一代低延迟语音/多模态模型的主流架构选择,替代部分Transformer应用场景
  • 价格竞争加剧:Sonic-3.6以ElevenLabs一半价格提供同等或更优质量,将加速TTS市场 commoditization,推动行业从"声音库竞争"转向"引擎性能竞争"
  • 语音代理落地加速:从IVR替换、入站/出站支持代理到销售培训模拟器,语音交互正从辅助功能转变为核心产品能力,建议企业评估Sonic-3.6在客服、合规、多语言本地化场景的集成可行性

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Speech 语音 Product Launch 产品发布 Evaluation 评测 Inference 推理