ComfyUI Node
Fish Audio S2.1 Pro
A ComfyUI node in Runware/Audio/fishaudio with 18 inputs and 1 output.
Fish Audio S2.1 Pro
- speech
- audioSettings
- referenceVoices
- audio
◄numberResults1►
◄settings.chunkLength300►
◄settings.conditionOnPreviousChunkstrue►
◄settings.earlyStopThreshold1.00►
◄settings.latencynormal►
◄settings.maxTokens1024►
◄settings.minChunkLength50►
◄settings.normalizetrue►
◄settings.normalizeLoudnesstrue►
◄settings.repetitionPenalty1.20►
◄settings.temperature0.70►
◄settings.topP0.70►
◄ttlfalse►
◄ttl_value60►
◄outputFormatMP3►
CategoryRunware/Audio/fishaudio
Inputs (18)
| Name | Type | Default | Description |
|---|---|---|---|
| speech | RUNWARE_SPEECH | — | |
| audioSettingsopt | RUNWARE_AUDIOSETTINGS | — | |
| referenceVoicesopt | RUNWARE_REFERENCEVOICES | — | |
| numberResultsopt | INT | 11–4 | Number of results to generate. Each result uses a different seed, producing variations of the same parameters. |
| settings.chunkLengthopt | INT | 300100–300 | Text segment size for processing. |
| settings.conditionOnPreviousChunksopt | BOOLEAN | true | Previous audio context for voice consistency across chunks. |
| settings.earlyStopThresholdopt | FLOAT | 1.000–1 | Early stopping threshold for batch processing. |
| settings.latencyopt | COMBO | normal | Latency / quality trade-off. |
| settings.maxTokensopt | INT | 10241–4294967295 | Maximum audio tokens to generate per text chunk. |
| settings.minChunkLengthopt | INT | 500–100 | Minimum characters before splitting into a new chunk. |
| settings.normalizeopt | BOOLEAN | true | Text normalization for English and Chinese. Improves stability for numbers. |
| settings.normalizeLoudnessopt | BOOLEAN | true | Normalize output loudness for consistent perceived volume. |
| settings.repetitionPenaltyopt | FLOAT | 1.200–2 | Penalty for repeating audio patterns. |
| settings.temperatureopt | FLOAT | 0.700–1 | Expressiveness of the generated speech. |
| settings.topPopt | FLOAT | 0.700.0001–1 | Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity. |
| ttlopt | BOOLEAN | false | Enable to set ttl. Off uses the model's default. |
| ttl_valueopt | INT | 60 | Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. |
| outputFormatopt | COMBO | MP3 | File format for the generated audio. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |