Get Started

Download

The most accurate speech API for developers

Avalon is the drop-in API tuned for how developers talk. Change two lines to upgrade from Whisper and get 97.3% accuracy on AISpeak—no hallucinated model names, no misheard commands, no rewrite of your stack.

Start transcribing

Documentation

OpenAI-compatible endpoints for streaming and batch transcription

Free until October 15th, 2025 — then $0.39 per hour of audio

AISPEAK

97%

Accuracy

Avalon nails AI jargon, CLI commands, and model names. Whisper Large v3 hits 65.1%.

OPENASR

7/8

Splits won

Leads Whisper Large v3 and ElevenLabs Scribe across public benchmarks developers trust.

DROP-IN

2-line

Swap

Swap your base URL and model name. Keep your auth headers, streaming logic, and tooling.

Why Avalon

People don't speak like an audiobook when they're prompting Claude Code or narrating a deploy. Most training data does. Avalon was trained on real developer workflows—pairing transcripts with CLI sessions and IDE captures—so it keeps the exact command, casing, and model number you said.

Benchmarking alone misses the point. We built Avalon after watching other models fumble obvious technical nouns—turning "zshrc" into "C sharp C" or hallucinating entirely new model names. Avalon stays literal, so your copilots, support analytics, and live demos sound like your users actually talk.

Stop hallucinations on AI terms

AISpeak is our benchmark of real-world clips where people say things like "Claude Code," "GPT-4o-mini," and "o3." Avalon transcribes the key term correctly 97.3% of the time. Whisper Large v3 misses it in more than one out of three attempts.

Accuracy on Coding and AI Terms

Higher is better

AISpeak-10

97.4%

Avalon

Top score

ElevenLabs Scribe

78.8%

Whisper Large v3

65.1%

Voxtral Mini 3B

59.5%

NVIDIA Canary 1B

51.5%

AISpeak-50

97.5%

Avalon

Top score

ElevenLabs Scribe

86.7%

Whisper Large v3

82.4%

Voxtral Mini 3B

79.4%

NVIDIA Canary 1B

71.8%

AISpeak-500

95.8%

Avalon

Top score

ElevenLabs Scribe

87.5%

Whisper Large v3

84.9%

Voxtral Mini 3B

82.9%

NVIDIA Canary 1B

74.1%

Whisper hallucinates. Avalon doesn't.

Avalon

I've

tried

running

this

with

GPT-4o,

GPT-4.1,

and

o3.

Whisper

I've

tried

running

this

with

GPT-4.0,

GPT-4.1,

and

GPT-03.

Avalon

Claude 4

announcement.

Whisper

Claude for

announcement.

Parakeet

cloud floor

announcement.

Avalon

just

tried

running

this

with

GPT-4o

and it didn't go very well.

Whisper

I just tried running this with

GPT-400,

and it didn't go very well.

Avalon

Ultrathink.

Whisper

Ultrathing.

Clips pulled from AISpeak evaluations

Proven on industry benchmarks

Avalon leads Whisper Large v3, ElevenLabs Scribe, and AssemblyAI across OpenASR. The same accuracy shows up in production: teams building copilots, onboarding agents, and support analytics already rely on Avalon to keep transcripts literal.

Lower is better. Avalon wins the majority of public datasets developers reference when validating speech models.

Beats Whisper Large v3 on 7 of 8 OpenASR splits developers cite most often.

Tops ElevenLabs Scribe and AssemblyAI on the same public benchmarks.

Change two lines, keep your workflow

Avalon mirrors OpenAI's Whisper API — same request format, same response shape. Point your existing integration at the Avalon endpoint and keep shipping.

Python

Node.js

cURL

from openai import OpenAI

client = OpenAI(
    api_key="your-avalon-api-key",
    base_url="https://api.aqua.sh/v1"
)

audio_file = open("speech.mp3", "rb")
transcript = client.audio.transcriptions.create(
    model="avalon-1",
    file=audio_file
)

print(transcript.text)