FunAudioLLM: CosyVoice2-0.5B

CosyVoice 2 is a streaming speech synthesis model based on a large language model, employing a unified streaming/non-streaming framework design. The model enhances the utilization of the speech token…

siliconFlow/FunAudioLLM/CosyVoice2-0.5B

CosyVoice 2 is a streaming speech synthesis model based on a large language model, employing a unified streaming/non-streaming framework design. The model enhances the utilization of the speech token codebook through finite scalar quantization (FSQ), simplifies the text-to-speech language model architecture, and develops a chunk-aware causal streaming matching model that supports different synthesis scenarios. In streaming mode, the model achieves ultra-low latency of 150ms while maintaining synthesis quality almost identical to that of non-streaming mode. Compared to version 1.0, the pronunciation error rate has been reduced by 30%-50%, the MOS score has improved from 5.4 to 5.53, and fine-grained control over emotions and dialects is supported. The model supports Chinese (including dialects: Cantonese, Sichuan dialect, Shanghainese, Tianjin dialect, etc.), English, Japanese, Korean, and supports cross-lingual and mixed-language scenarios.

Specifications & capabilities

Input
text
Output
speech
Capabilities
speechOutput

Published prices

1–1 / 1

FunAudioLLM/CosyVoice2-0.5B ↗

$7.15

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
utf8_bytes_per_million
Currency
USD
Billing conditions
Billing label
M UTF-8 bytes

Provider specifications & access

1–1 / 1

FunAudioLLM/CosyVoice2-0.5B ↗

source model id
FunAudioLLM/CosyVoice2-0.5B
hosting
siliconflow-hosted
platforms
  • SiliconFlow
architecture
input_modalities
  • text
output_modalities
  • speech
capabilities

    Source specification observations

    1–1 / 1

    siliconFlow ↗

    field
    context_length
    value
    0K
    scope
    source-model
    source id
    siliconFlow
    confidence
    1

    Original sources

    1–4 / 4

    SiliconFlow · Model page ↗

    SiliconFlow · Playground ↗

    SiliconFlow · API documentation ↗

    SiliconFlow · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace