Ava · Conversational AI
Warm, natural and expressive, for conversational agents and apps that talk with people all day.
Ultra realistic TTS at 10x cheaper than ElevenLabs
Studio-quality text-to-speech for developers and teams. Same natural voices, a fraction of the cost.
Zero Data Retention by Default No Training Unless You Opt In Private Voice ClonesDevelopers
$0.0075 / Minute
— Natural-Sounding Voices
— 50+ Voices Supported
— Real-Time Streaming
— Voice Cloning
— Unlimited Characters
— 24/7 Support
Enterprise
Contact Us
— All Developer Features Included
— Dedicated Infrastructure
— Priority Support & SLA
— Volume Discounts
— Custom Voice Design
— Early Access to New Voices
Expressive voice design
Natural-sounding voices for every use case. Preview each voice and find the perfect match for your project.
v1
Production. Fast, stable, real-time streaming.
Katie · Customer Support
Clear and reassuring, ideal for support lines and service interactions.
Sophie · Gaming & Interactive
Bright and energetic, made for games, streams and interactive experiences.
v2 Preview
Direct the performance: emotions, laughs, sighs and whispers.
Mia · Wellness & Coaching
Soft, calm and close. Great for meditation, wellness and coaching apps.
Chloe · Social & Entertainment
Quick, chatty and fun, for streaming, social apps and entertainment.
Zander · Narration
Low, warm and expressive, for audiobooks, podcasts and narrative content.
Ethan · Healthcare & Onboarding
Gentle and steady, for healthcare, onboarding and sensitive conversations.
Direct the delivery inline with cues like {excited}, {laughs} or {whisper}…{/whisper}. See the docs ›
Price Comparison
Iodine $0.0075 / min
Google Gemini 3.8 Flash TTS $0.0137 / min
OpenAI gpt-4o-mini-tts $0.0145 / min
Fish Audio S2.1 Pro $0.015 / min
xAI Grok TTS $0.015 / min
Deepgram Aura-2 $0.03 / min
Cartesia Sonic-3.6 $0.038–0.065 / min
ElevenLabs v4 Turbo $0.04 / min
Deepgram Flux TTS $0.045 / min
Fish Audio Drama 3 $0.05 / min
OpenAI Realtime $0.0768 / min
ElevenLabs v4 $0.08 / min
xAI Grok Voice 3.0 $0.08 / min
Based on each provider's published pay-as-you-go API rates as of Nov 2026, assuming ~1,000 characters per minute of audio.
Savings Calculator
See how much you save by switching to Iodine
1k hrs
10 hrs 1M hrs
ElevenLabs v4 Turbo cost $2,400
Iodine cost $450
Your monthly savings $1,950 (81%)
Your yearly savings $23,400
Speech to Text Up to 40× cheaper
Transcribe recordings on the same API key and credit balance.
$0.00015 / Minute
OpenAI Whisper $0.006 / Minute
Deepgram Nova-3 $0.0043 / Minute
AssemblyAI Universal-2 $0.0025 / Minute
Iodine $0.00015 / Minute
Speed ~175× real time
Formats WAV, MP3, FLAC, OGG
Languages 99
OpenAI-Compatible Yes
Audio Stored Never
Performance Metrics
TTFB <250ms
Uptime 99.9%
Global Regions 3
Avg Response Time 190ms
Concurrent Connections Unlimited
Privacy & Data
Data Retention Zero (ZDR by default)
Text & Audio Stored Never, unless you opt out
Training on Your Data Opt-in only
Cloned Voices Private, never trained on
Encryption In transit & at rest
Included with all plans
- Zero Data Retention
- Unlimited Streams
- Abuse Protection
- 24/7 Email Support
Frequently asked questions
Everything you need to know before joining—especially if you're new to design engineering or shifting from a pure design or dev background.
Our custom models are built on a transformer backbone paired with our own neural audio codec. This architecture delivers natural, expressive speech with low latency and high efficiency.
Yes. Our models are proprietary and closed source, which allows us to maintain quality control, security, and continuous improvements without exposing our core IP.
We support a wide range of voices. Our custom-trained models cover major accents, with new voices added regularly. Contact us for a full list of supported languages.
Yes. We offer custom voice cloning and training services for enterprise customers. You can create unique, branded voices that match your identity and use case.
Yes. Send a recording (WAV, MP3, FLAC or OGG, up to 10 minutes) to /v1/stt and get the transcript back, at $0.009 per hour of audio from the same credit balance. The endpoint is OpenAI-compatible, so existing transcription code works by changing the base URL. Recordings are transcribed in memory and never stored.
Yes. Enterprise plans can run on dedicated capacity reserved for your traffic, with priority support and SLAs.
We operate in data centers across multiple regions globally. This ensures low latency, high availability, and compliance with regional data regulations.
We offer enterprise-grade SLAs with 99.9%+ uptime. Our multi-region infrastructure provides redundancy and failover to ensure consistent service availability.
Not by default. Zero Data Retention (ZDR) is on for every account and API key: your text is processed in memory and discarded, and generated audio is streamed back without a copy being kept. We only log request metadata (character count, audio length, voice, latency) for billing and usage stats. ZDR stays on unless your account owner chooses to turn it off in the console.
Not unless you opt in. With ZDR on (the default) we never use your text or audio for training. If your account owner turns ZDR off, requests are kept and may be used to improve our models. You can turn it back on and delete kept data at any time. Cloned voices are never used for training.
All traffic is encrypted in transit with TLS and stored data is encrypted at rest. API keys and session tokens are stored only as hashes. See our privacy policy for the full details, and contact us for specific enterprise compliance requirements.
Our optimized infrastructure delivers under 200ms latency for most requests. For real-time streaming use cases, we offer low-latency endpoints designed for conversational AI and live applications.
We offer pay-as-you-go pricing, volume discounts, and custom enterprise plans. Contact our sales team for a quote tailored to your usage and requirements.