# Gemini 2.5 Pro TTS (Achird) regression: Audio bumps and pitch jumps between sentences **URL:** \ **Category:** Google AI Studio\ **Tags:** model\ **Created:** [September 23, 2026, 8:11am UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-achird-regression-audio-bumps-and-pitch-jumps-between-sentences/184468 "2026-09-23T08:11:15Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Rayba](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/rayba/32/150722_2.png) [@Rayba](https://discuss.ai.google.dev/u/Rayba)\ **Post date:** [September 23, 2026, 8:11am UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-achird-regression-audio-bumps-and-pitch-jumps-between-sentences/184468/1 "2026-09-23T08:11:15Z")
Hi team, ​I have been using the Gemini 2.5 Pro preview TTS model with the Achird voice for content narration. Previously, the output was consistent and clear. ​In recent builds, there is a noticeable regression: ​Sudden volume bumps and pitch jumping at sentence boundaries. ​Degraded voice clarity compared to earlier versions. ​Is this a known checkpoint issue in the preview model? Are there any recommended prosody/style parameters or stable checkpoints available to eliminate these sentence jumps? ---
**Author:** ![Pooja\_Kapse](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/pooja_kapse/32/24754_2.png) [@Pooja\_Kapse](https://discuss.ai.google.dev/u/Pooja_Kapse)\ **Post date:** [September 28, 2026, 6:18am UTC](https://discuss.ai.google.dev/t/gemini-2-5-pro-tts-achird-regression-audio-bumps-and-pitch-jumps-between-sentences/184468/2 "2026-09-28T06:18:49Z")
Hello @Rayba , We have just launched the new Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) and Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) models: [Google AI Studio](https://aistudio.google.com/docs/speech-generation). Could you please test with gemini-3.8-flash-tts and let us know if you are still experiencing the same audio issue?