Speech-to-Text

Transcribe audio to text with Venice speech-to-text models and /audio/transcriptions.

Speech-to-text transcribes spoken audio into written text. Send an audio file to /audio/transcriptions, choose a transcription model, and select the response format you want back.

Working with a recording of a conversation? Meeting Notes with Speech to Text goes from an audio file to decisions and action items that cite the second they were agreed, including which models return segment timings and how to handle a transcript that never says who is speaking.

Basic Usage

Python

import os

import requests

with open("meeting.mp3", "rb") as audio:
    response = requests.post(
        "https://api.venice.ai/api/v1/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['VENICE_API_KEY']}"},
        files={"file": audio},
        data={
            "model": "nvidia/parakeet-tdt-0.6b-v3",
            "response_format": "json",
        },
    )

response.raise_for_status()
print(response.json()["text"])

Supported Inputs

Common audio formats include mp3, mp4, mpeg, mpga, m4a, wav, webm, flac, and ogg. See the Speech-to-Text Models page for current model support and pricing.

Response Formats

Format	Use when
json	You want a simple { "text": "..." } response.
text	You want plain text without JSON parsing.
srt	You need SubRip subtitles.
vtt	You need WebVTT subtitles.
verbose_json	You need richer timestamp and segment metadata.

Use subtitle formats when the transcript will be paired with media playback. Use json or text when the transcript feeds summarization, search, or downstream chat prompts.

Production Tips

• Keep audio clear and avoid overlapping speakers when possible.
• Split very long recordings into smaller chunks if your workflow needs lower latency or easier retries.
• Store the original audio path, model ID, and response format with each transcript for auditability.

Related Resources

• Audio Transcriptions API
• Speech-to-Text Models
• Text-to-Speech Guide