← All articles

#voxtral

9 articles

All articles tagged "voxtral" — self-hosted AI fixes, setups, and architecture notes.

Voxtral Capped at 3/10: Picking the Next Open TTS

Voxtral Capped at 3/10: Picking the Next Open TTS

Eight engineering fixes deep, three weeks of patches, two failure modes on the same engine. The Voxtral open checkpoint has no path to release-quality podcast audio. The drama of staying with it anyway, and the three engines I plan to spike next.

Read article →
Per-block ffmpeg loudnorm averages multiple speakers to one gain, leaving the quieter voice quieter. Dynamic-mode loudnorm eats the first 3 seconds of audio.
fixdevopstts

Per-Segment Loudnorm and the 3-Second Lookahead Bug

Per-block ffmpeg loudnorm averages multiple speakers to one gain, leaving the quieter voice quieter. Dynamic-mode loudnorm eats the first 3 seconds of audio.

The intro music wasn't playing for the first four seconds of every podcast episode. RMS at minus infinity. The fix was one keyword, eval=frame.
fixdevopspodcast

FFmpeg Volume Filter eval=frame: A 4-Second Silent Bug

The intro music wasn't playing for the first four seconds of every podcast episode. RMS at minus infinity. The fix was one keyword, eval=frame.

Voxtral 4B advertises voice cloning, accepts ref_audio in the API, then crashes the engine because the encoder weights live only in Mistral's hosted product.
fixmistralpodcasttts

Voxtral 4B Open-Checkpoint: The Encoder is Gated

Voxtral 4B advertises voice cloning, accepts ref_audio in the API, then crashes the engine because the encoder weights live only in Mistral's hosted product.

Rendering a 367-character podcast turn as one Voxtral call takes 21 seconds. Split into 90-character chunks: 35 seconds. Same words, same voice, 38 percent more wallclock.
strategydevopspodcasttts

Voxtral Chunk Strategy: 38 Percent Faster Render with Whole Turns

Rendering a 367-character podcast turn as one Voxtral call takes 21 seconds. Split into 90-character chunks: 35 seconds. Same words, same voice, 38 percent more wallclock.

How we fixed loudness pumping, markup stripping, and dialogue rhythm in a self-hosted podcast pipeline
fixdevopspodcast

Voxtral Podcast Audio: Mono 24 kHz Baseline and Three Compression Pitfalls

How we fixed loudness pumping, markup stripping, and dialogue rhythm in a self-hosted podcast pipeline

How a silent AttributeError nearly killed our TTS pipeline, and why three lines of code fixed it forever.
fixdevopstts

Voxtral-TTS Blocker on GB10: The Three-Line vllm-omni Patch

How a silent AttributeError nearly killed our TTS pipeline, and why three lines of code fixed it forever.

How a three-line Python init order bug masqueraded as a Blackwell GPU hang, and why checking raw logs beat all hardware theories.
fixdevopsmistralpodcasttts

The 3.5-Hour Deadlock That Was Really an AttributeError

How a three-line Python init order bug masqueraded as a Blackwell GPU hang, and why checking raw logs beat all hardware theories.

How a single flag killed my self-hosted TTS stack, and how I fixed it without losing a second of audio.
fixdevopspodcasttts

Voxtral Stage 1 OOM on GB10: Why --enforce-eager Is Not Enough

How a single flag killed my self-hosted TTS stack, and how I fixed it without losing a second of audio.