Bring your own voice
Import any Fish Audio voice by ID, including clones, and reuse it across every Retell agent you run.
Fish Audio voices inside Retell AI agents
Retell supports fish_audio as a voice provider, so any Fish Audio voice, including the clones you make, can answer the phone for your agents.
CategoryVoice agent platform
IntegrationVoice provider (fish_audio)
How to addAdd Voice API or the Retell dashboard
VoicesAny Fish Audio voice ID, including clones
In productionFish Audio S2 Pro powers Retell deployments
Add Voice API ↗Why Retell AI and Fish Audio
Retell runs the call: telephony, turn-taking, interruptions and orchestration. Fish Audio decides how the agent sounds. That split lets teams ship phone agents in days and tune the voice independently.
Built for phone calls
Retell handles the telephony stack and conversation flow; Fish Audio's streaming keeps responses natural on the line.
Proven at production scale
Fish Audio S2 Pro powers production deployments at Retell AI, handling real traffic, edge-case pronunciation and multi-region load.
How it works
3 steps from a Fish Audio voice to a shipping product on Retell AI.
STEP 01
Pick a voice in Fish Audio
Choose a library voice or clone your own from 30 seconds of audio, then copy its voice ID.
STEP 02
Add it to Retell
Call Add Voice with voice_provider set to fish_audio and your Fish Audio voice ID, or add it from the dashboard.
JSON
12345
{ "voice_provider": "fish_audio", "provider_voice_id": "<fish_audio_voice_id>", "voice_name": "Mana"}STEP 03
Assign it to an agent
Select the new voice on any Retell agent. Every call from that agent now speaks with Fish Audio.
What teams build with Fish Audio and Retell AI
Inbound support lines
Answer every call instantly with an agent that sounds like your brand, not a robot.
Appointment reminders
Outbound confirmations and reschedules that customers actually pick up and finish.
Lead qualification
Warm, natural first conversations that hand qualified leads to a human rep.
More partners
Open-source WebRTC stack and Agents framework. Fish Audio TTS ships as a first-party plugin and through LiveKit Inference.
Real-time infrastructure
AI video platform. Fish Audio powers the Fish voice engine inside HeyGen's AI Studio, with accent and locale controls for English. Available in both HeyGen Video Creator and LiveAvatar.
Video & avatars
Global execution layer for real-time voice AI. Runs Fish Audio S2.1 Pro on in-region GPUs in Europe and Australia.
Regional inference
Start building with Fish Audio and Retell AI
Read the Add Voice reference, or talk to our partnerships team about joint customers and co-marketing.