Fish AudioFish Audio S2 Pro
88%?
SECOND MODELChoose a model above
Its column will appear here when selected.
OverviewFish Audio S2 ProSecond model
PriceFree tier available · API from $15/1M UTF-8 bytes—
SpecializationTTS · Voice Cloning · Multilingual Speech · Emotion Control · Real-time Audio—
QualityHighly expressive speech with fine-grained control over prosody, emotion, pacing and delivery.—
FeaturesVoice Cloning · API · Streaming · Multilingual · Emotion Control—
Capabilities
14 specifications +
SpecificationFish Audio S2 ProSecond model
Number of voicesNot specifiedNot specified
Text-to-SpeechYesNot specified
Voice cloningInstant voice cloning supportedNot specified
DubbingSupported through Fish Audio workflowsNot specified
Supported languages80+ languagesNot specified
Voice conversionNot listed as a core S2 Pro capabilityNot specified
Real-time audioYes · streamingNot specified
Emotion controlOpen-ended natural-language direction tagsNot specified
Voice designAvailable through Fish Audio platform plansNot specified
Speech-to-SpeechNot listed as a core S2 Pro capabilityNot specified
Voice libraryAvailable through Fish Audio platformNot specified
Emotion Control15,000+ open-ended direction tagsNot specified
Voice CloningInstant voice cloningNot specified
Voice DesignAvailable on platform plansNot specified
Developer
3 specifications +
SpecificationFish Audio S2 ProSecond model
SDK availabilityPython; TypeScriptNot specified
API AccessREST APINot specified
Commercial usePlatform plans allow commercial use; open weights require commercial licenseNot specified
Developer & Integration
1 specifications +
SpecificationFish Audio S2 ProSecond model
API AccessREST API availableNot specified
Commercial & Business
1 specifications +
SpecificationFish Audio S2 ProSecond model
Commercial UsePlatform plans allow commercial use; open weights require commercial licenseNot specified
Pricing
4 specifications +
SpecificationFish Audio S2 ProSecond model
Free Plan$0/month · 8,000 credits · up to 7 minutesNot specified
Pricing modelSubscription or API pay-as-you-go ($15/1M UTF-8 bytes)Not specified
Paid plansPlus $11 annual/$15 monthly · Pro $75 annual/$100 monthly · Max $749 annual/$999 monthlyNot specified
Free plan$0/month · 8,000 credits · up to 7 minutesNot specified
Voice cloning
2 specifications +
SpecificationFish Audio S2 ProSecond model
Voice cloning modesInstant; Enhanced/Professional via platformNot specified
Minimum cloning sample durationShort reference audio; 30 seconds recommended on production pageNot specified
Performance
1 specifications +
SpecificationFish Audio S2 ProSecond model
API latency<150 ms first audio (cloud)Not specified
Output
1 specifications +
SpecificationFish Audio S2 ProSecond model
Streaming supportYes · WebSocketNot specified
Languages & Voices
1 specifications +
SpecificationFish Audio S2 ProSecond model
Voice Library2M+ community voicesNot specified
Similar AI models
Cartesia
Cartesia Sonic
Real-time AI text-to-speech model for natural, low-latency voice generation and voice cloning.
Free $0/month · Paid from $5/month
KreadoAI
KreadoAI
AI content platform with instant voice cloning, multilingual TTS and digital-avatar video tools.
Free plan · Instant voice clone $9.90
MiniMax
MiniMax Speech 2.8
High-fidelity multilingual text-to-speech and rapid voice cloning for expressive AI audio.
API from $60/1M chars · Voice clone $1.50
Resemble AI
Chatterbox Multilingual
Open-source multilingual text-to-speech and zero-shot voice cloning model by Resemble AI.
Free · Open source (MIT)
Murf AI
Murf AI
AI voice platform for professional TTS, instant and professional voice cloning, dubbing and real-time agents.
Free trial · API pay-as-you-go · Enterprise cloning
Uberduck
