|
BUG: Gemini 3.8 Live API overrides language_code / ignores system prompt accent formatting
|
|
1
|
41
|
September 29, 2026
|
|
UI Bug: Audio Settings dropdowns (Pace, Accent, Voice Style) not selecting or applying in Google AI Studio
|
|
1
|
42
|
September 29, 2026
|
|
Incorrect PROHIBITED_CONTENT classification
|
|
3
|
53
|
September 29, 2026
|
|
Repeated image-to-video audio failures on Veo 3.1 Lite and Fast
|
|
1
|
29
|
September 29, 2026
|
|
Gemini-3.8-flash-tts Trailing Static / Scratch Noise Artifact at Sentence & Turn Boundaries
|
|
0
|
10
|
September 29, 2026
|
|
Lyria 3.5 returns unexplained PROHIBITED_CONTENT for original fictional songs
|
|
0
|
10
|
September 28, 2026
|
|
Gemini Live API: input_audio_transcription returns incorrect text while model correctly processes audio
|
|
13
|
635
|
September 25, 2026
|
|
Pricing of Speech to Speech live model
|
|
7
|
980
|
September 24, 2026
|
|
Gemini 3.8 Voice Replication: POST /v1beta/voices returns 500 INTERNAL with REST and google-genai 2.25.0
|
|
1
|
73
|
September 24, 2026
|
|
Can a licensed synthetic TTS voice be used as reference audio for Gemini 3.8 Flash TTS Voice Replication?
|
|
0
|
37
|
September 24, 2026
|
|
Gemini 3.8 Live support for Voice Design / custom voices
|
|
0
|
56
|
September 24, 2026
|
|
Gemini 3.1 Flash TTS bills AUDIO tokens for minutes of digital silence
|
|
3
|
90
|
September 21, 2026
|
|
[CRITICAL BUG] Google AI Studio UI Brick: Gemini 2.5 Pro Missing & Voice/Audio Models Completely Glitching
|
|
0
|
61
|
September 21, 2026
|
|
Gemini Live API: acoustic echo cancellation needed for SIP telephony deployments
|
|
1
|
201
|
September 21, 2026
|
|
Does the paid plan allow longer continuous Gemini TTS audio generation?
|
|
1
|
43
|
September 18, 2026
|
|
Gemini 2.5 Native Dialog audio problems
|
|
36
|
3201
|
September 17, 2026
|
|
Gemini 3.1 Flash Live Preview — persistent high-pitched / dial-up-like audio distortion
|
|
8
|
272
|
September 15, 2026
|
|
Gemini-3.1-flash-tts-preview: streamGenerateContent truncates audio + finishReason: OTHER past ~60s, while generateContent (non-streaming) works
|
|
6
|
479
|
September 14, 2026
|
|
GA / Production Release Timeline for gemini-3.1-flash-live-preview on Vertex AI
|
|
1
|
542
|
September 11, 2026
|
|
Requesting allowlist access for lyria-3-pro-preview (Music to Music / Audio Input)
|
|
1
|
52
|
September 8, 2026
|
|
Live API (BidiGenerateContent) hard closures + severe latency — CONTENT_TYPE_AUDIO error, close code 1007
|
|
4
|
175
|
September 7, 2026
|
|
[gemini-3.5-transcribe] Documented custom_vocabulary + diarization/timestamps configuration is rejected by the Interactions API
|
|
2
|
118
|
September 1, 2026
|
|
Audio transcription regression: Gemini 3.5 Flash-Lite has 3.55× higher WER than 3.1 Flash-Lite on a french radiology test dataset
|
|
0
|
85
|
August 29, 2026
|
|
Gemini-3.1-flash-tts-preview generates near-silent audio despite finish_reason=STOP
|
|
1
|
106
|
August 28, 2026
|
|
3.5-flash-lite is slower than 3.1-flash-lite on audio input
|
|
1
|
149
|
August 13, 2026
|
|
[Bug] Gemini 3 Flash and 3.1 Pro: Progressive timestamp drift in audio transcription
|
|
7
|
947
|
August 13, 2026
|
|
Gemini 3.1 Flash Live — Great upgrade from 2.5, two model behavior observations from production voice app
|
|
19
|
2113
|
August 11, 2026
|
|
Can Gemini Speech models preserve voice identity while reducing a foreign accent in prerecorded videos?
|
|
0
|
52
|
August 7, 2026
|
|
I want to transcribe audio data
|
|
1
|
91
|
July 20, 2026
|
|
Live API / Realtime / Audio
|
|
1
|
201
|
July 8, 2026
|