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.
- OpenAI-compatible endpoints for streaming and batch transcription
- Free until October 15th, 2025 — then $0.39 per hour of audio
AISpeak
97.3% 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.
- ElevenLabs Scribe78.8%
- Whisper Large v365.1%
- Voxtral Mini 3B59.5%
- NVIDIA Canary 1B51.5%
- ElevenLabs Scribe86.7%
- Whisper Large v382.4%
- Voxtral Mini 3B79.4%
- NVIDIA Canary 1B71.8%
- ElevenLabs Scribe87.5%
- Whisper Large v384.9%
- Voxtral Mini 3B82.9%
- NVIDIA Canary 1B74.1%
Whisper hallucinates. Avalon doesn't.
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.
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)Simple pricing
Avalon API
Everything unlocked. No minimums.
- Billed per second, streaming or batch
- No overages, no enterprise gatekeeping
- Includes speaker labels and timestamps
Start building with Avalon
Spin up your Avalon API key and launch features where transcripts stay literal—in demos, copilots, and support workflows.