Transcription
The current adapter uses Fish Audio transcribe-1. Supply audio as an accessible URL or a local file through the CLI, and use automatic language detection or a language code. The returned transcript can feed a separate summarization task, such as extracting decisions and action items from an interview.
Inputs & outputs
Transcription
The current adapter uses Fish Audio transcribe-1. Supply audio as an accessible URL or a local file through the CLI, and use automatic language detection or a language code. The returned transcript can feed a separate summarization task, such as extracting decisions and action items from an interview.
Audio input
The adapter accepts an audio URL or base64 bytes. The CLI reads local files into base64; the configured audio size limit is 50,000,000 bytes.
Language and result
language defaults to auto. The adapter returns text, detected or requested language, and provider.
Timestamps and subtitles
The adapter explicitly sends ignore_timestamps: true. It does not produce SRT or speaker labels, even though the CLI catalog lists a format option.
Pricing
Tool usage
Tool charges use the same configured cost basis and 2× multiplier as billing. Model and runtime charges are separate.
The charge follows the operation and billable units shown here.
fish-audio.transcribe
$0.0002 per second.
Example tasks
Put it to work
Choose an example and adapt its input and intended result to your task.
Transcribe a meeting
Transcribe this recording faithfully. Flag unclear passages and preserve names and numbers without guessing.
Extract follow-ups
Transcribe this audio, then list decisions and follow-up actions separately. Cite timestamps only if the transcript provides them.
Common questions