Audio modelOpen weights
Fish Audio S2 Pro
Fish Audio
- Released
- March 9, 2026
- Data date
- October 3, 2026
- Model class
- Access
Fish Audio S2 Pro is an open speech synthesis model controlled through prosody and emotion tags. It supports multi-speaker dialogue, voice cloning, and broad language coverage, while the released S2 line is presented for API and local-weights use.
Fish Audio cites about 100 milliseconds to first audio. The official S2 sources cite roughly 50 to 80 languages.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Speech synthesisSource |
| Access | API and local weightsSource |
| Input | Text with prosody and emotion tagsSource |
| Output | Multilingual speechSource |
| Checkpoint | fishaudio/s2-proSource |
| Languages | About 50 to 80 languages depending on the documentation variantSource |
| Latency | About 100 milliseconds to first audioSource |
| Features | Inline prosody, emotion, multi-speaker dialogue, and voice cloningSource |
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
win rate (Show measurement, test conditions, and source)
- Source value
- 81.88
- Score
- 81.88
- Metric
- win rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Fish Audio S2 announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Provider listening evaluation
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Fish Instruction Benchmark task acceptance rate (Show measurement, test conditions, and source)
- Source value
- 93.3
- Score
- 93.3
- Metric
- accuracy
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Fish Audio S2 announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Provider benchmark
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Seed-TTS Eval WER, Chinese (Show measurement, test conditions, and source)
- Source value
- 0.54
- Score
- 0.54
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Fish Audio S2 announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Provider S2 evaluation
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Seed-TTS Eval WER, English (Show measurement, test conditions, and source)
- Source value
- 0.99
- Score
- 0.99
- Metric
- word error rate
- Unit
- %
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Lower is better
- Source type
- vendor-reported
- Evaluator
- Fish Audio S2 announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Provider S2 evaluation
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Fish Instruction Benchmark quality (Show measurement, test conditions, and source)
- Source value
- 4.51
- Score
- 4.51
- Metric
- score
- Unit
- rating
- Benchmark version
- source version not stated
- Category
- audio
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Fish Audio S2 announcement
- Status
- active
- Retrieved at
- 2026-10-04
- Methodology
- Vendor-reported result. Provider benchmark
- Context
- Source-specific observation; it does not establish a compatible cross-model cohort.
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Additional source | Fish Audio S2 open-source announcement (retrieved October 3, 2026; October 4, 2026) · Fish Audio S2 open-source announcement · Editorial description reviewed October 3, 2026 |
| Additional source | Fish Audio S2.1 API announcement (retrieved October 3, 2026) · Fish Audio S2.1 API announcement · Editorial description reviewed October 3, 2026 |