You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Huge difference between output of original PocketTTS and Kotlin API #3172
I have noticed that there is a huge difference in the generated TTS audio output of the original Python implementation by Kyutai and the sherpa-onnx Kotlin API (I've only tested the Kotlin API so far so I can't speak about the others).
Hi @WaelShaikh! I'm Dosu and I’m helping the sherpa-onnx team.
The sherpa-onnx documentation for the Kotlin API doesn't list all available hyperparameters for Kyutai TTS, but based on related TTS models, parameters like speaker ID (sid), length scale (vits-length-scale), and rule-based text normalization (tts-rule-fsts) can impact output quality, in addition to numSteps, temperature, and chunk_size that you're already using. These parameters are commonly exposed in CLI and Python APIs, but it's unclear if they're available in the Kotlin API without checking the source code or API docs.
To improve quality, try increasing numSteps, adjusting temperature, and experimenting with chunk_size. If your model or API supports it, try setting sid (for speaker selection), vits-length-scale (for speech speed/prosody), or enabling rule-based normalization for numbers and dates. The lack of Kyutai-specific tuning guidance in the docs means some trial and error may be needed, and reviewing the Kotlin API source or comparing with the original Python implementation could reveal more tunable options.
I was using the int8 version of the model. Using the full precision model does significantly improve quality even at 1 inference step. Also increasing chunk size to 50 also helps.
Activity
dosubot commentedon Feb 11, 2026
Hi @WaelShaikh! I'm Dosu and I’m helping the sherpa-onnx team.
The sherpa-onnx documentation for the Kotlin API doesn't list all available hyperparameters for Kyutai TTS, but based on related TTS models, parameters like speaker ID (
sid), length scale (vits-length-scale), and rule-based text normalization (tts-rule-fsts) can impact output quality, in addition tonumSteps,temperature, andchunk_sizethat you're already using. These parameters are commonly exposed in CLI and Python APIs, but it's unclear if they're available in the Kotlin API without checking the source code or API docs.To improve quality, try increasing
numSteps, adjustingtemperature, and experimenting withchunk_size. If your model or API supports it, try settingsid(for speaker selection),vits-length-scale(for speech speed/prosody), or enabling rule-based normalization for numbers and dates. The lack of Kyutai-specific tuning guidance in the docs means some trial and error may be needed, and reviewing the Kotlin API source or comparing with the original Python implementation could reveal more tunable options.Reference: sherpa-onnx TTS model parameters
To reply, just mention @dosu.
Share context across your team and agents. Try Dosu.
WaelShaikh commentedon Feb 11, 2026
Update:
I was using the int8 version of the model. Using the full precision model does significantly improve quality even at 1 inference step. Also increasing chunk size to 50 also helps.
Closing this.
ramlakk commentedon Feb 14, 2026
@WaelShaikh Can You Share The Configs? Wav File Attributes Like What Kind Of Audio Is Used?
fix(huddle): switch Pocket TTS to fp32 model bundle