From 698a166cdf766cbfcdfadc90a351ff3cf0b4f75d Mon Sep 17 00:00:00 2001 From: 404oops Date: Thu, 15 Oct 2026 09:38:41 +0200 Subject: [PATCH] Clarify transcription language results and omit pricing --- src/docs/src/AI/speech2txt.md | 2 +- src/docs/src/Objects/speech2txtresult.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/src/docs/src/AI/speech2txt.md b/src/docs/src/AI/speech2txt.md index f8ad8770e..a4968b9ce 100644 --- a/src/docs/src/AI/speech2txt.md +++ b/src/docs/src/AI/speech2txt.md @@ -64,7 +64,7 @@ Gemini rejects options it can't honor with `bad_request` instead of ignoring the Gemini accepts WAV, MP3, AIFF, AAC, OGG, FLAC, MPEG, M4A, L16, Opus, A-law, mu-law and WebM audio, sent with an `audio/*` MIME type (`audio/wav`, `audio/mpeg`, `audio/webm`, and so on). Other types fail with `bad_request`, and the audio isn't converted. The audio can be at most 10 MiB, or 1 hour long, or 30 minutes long with word timestamps or `diarize`. Gemini enforces the duration limits itself, and the call fails when the audio is longer. A transcript is limited to 8,192 output tokens. A longer one fails with `502 upstream_failed`, so split long recordings into shorter files. -Gemini is billed per token at $2 per million audio input tokens and $12 per million output tokens, thinking tokens included. Before transcribing, Puter reserves the cost of the counted audio tokens plus the full 8,192 output tokens, then charges the tokens Gemini reports. +Before transcribing, Puter reserves the cost of the counted audio tokens plus the full 8,192 output tokens, then charges the tokens Gemini reports. #### `testMode` (Boolean) (optional) diff --git a/src/docs/src/Objects/speech2txtresult.md b/src/docs/src/Objects/speech2txtresult.md index a9515b7f2..c5188410c 100644 --- a/src/docs/src/Objects/speech2txtresult.md +++ b/src/docs/src/Objects/speech2txtresult.md @@ -17,7 +17,7 @@ An optional string naming the model that produced the transcript. #### `language` (String) -An optional string containing the detected or specified language of the audio. Gemini includes `language` only when you pass one. +An optional string containing the detected or specified language of the audio. With Gemini, this field contains the `language` option you passed and is omitted otherwise. For OpenAI and xAI, whether it is present depends on the provider response. #### `segments` (Array)