Speech to Text

from fish_audio_sdk import Session, ASRRequest

session = Session("your_api_key")

# Read audio file
with open("audio.mp3", "rb") as f:
    audio_data = f.read()

# Transcribe
response = session.asr(ASRRequest(
    audio=audio_data
))

print(response.text)
print(f"Duration: {response.duration}ms")

# English transcription
response = session.asr(ASRRequest(
    audio=audio_data,
    language="en"
))

# Chinese transcription
response = session.asr(ASRRequest(
    audio=audio_data,
    language="zh"
))

response = session.asr(ASRRequest(
    audio=audio_data
))

# Full transcription
print(response.text)

# Segment details
for segment in response.segments:
    print(f"[{segment.start:.2f}s - {segment.end:.2f}s] {segment.text}")

# Include timestamps (default)
response = session.asr(ASRRequest(
    audio=audio_data,
    ignore_timestamps=False  # False = include timestamps
))

# Skip timestamp processing for faster results
response = session.asr(ASRRequest(
    audio=audio_data,
    ignore_timestamps=True   # True = skip timestamps
))

from fish_audio_sdk import TTSRequest

# Generate speech
audio_buffer = bytearray()
for chunk in session.tts(TTSRequest(
    text="Hello, this is a test"
)):
    audio_buffer.extend(chunk)

# Transcribe it
response = session.asr(ASRRequest(
    audio=bytes(audio_buffer)
))

print(response.text)

from fish_audio_sdk.exceptions import HttpCodeErr

try:
    response = session.asr(ASRRequest(
        audio=audio_data
    ))
except HttpCodeErr as e:
    if e.status_code == 413:
        print("Audio file too large (max 100MB)")
    elif e.status_code == 400:
        print("Invalid audio format")
    else:
        raise e