Fish Audio (@FishAudio) header
Fish Audio (@FishAudio) profile picture

AI voices you can't tell from humans. Expressive multilingual speech models and developer-first APIs. 👉 https://www.teapawt.org/t.co/gzh4M4drSq @FishCreativeHQ

San Francisco, CA
Joined April 2024
Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)Photo by Fish Audio (@FishAudio)
Introducing Fish Agent: a no-code platform to build custom AI voice agents that can make & take calls for you (median deploy time: 32s). Claim your free custom voice agent: s.fish.audio/vxhgs6 With Fish Agent, you can: > Build any voice agent by simply describing it. > Get a phone number or connect your own. > Power your agent with leading LLMs or integrate your custom LLM. > Connect tools, webhooks, knowledge, and more with full API access. > Enable natural, interruption-aware conversations with Fish Live 3 full-duplex voice model. From a personal AI assistant to a receptionist or customer support, build any voice agent you need. If you're an enterprise, book a demo and get a dedicated engineer to build with Fish: s.fish.audio/qh98e4 As part of the launch, we're giving away Fish agent platform credits for the next 48hrs. Just like, retweet , bookmark and reply "Live 3" to get yours.
672
635
333
2,143
3,747,552
Nobody binges a badly dubbed microdrama. The big reveal has to hit in 40 languages: same voice, same edge, same gasp. Proud to power the voices behind @plotpartyai's new Dubbing Studio. Congrats @xingsthatmatter & team. Building for creators or studios? Drama 3 is made for this.
We made 100 AI microdramas at @plotpartyai last month and we are opening our secrets so everyone can. Introducing…Plot Party Drama Studio, where one person can make a 60 minute drama in a couple hours. Comment with the drama idea you’d like to make and share the post, we will give 5 ultra plans (worth $100) to the most creative ones!
1
24
1,342
A to-do list that calls you → Grok Bot x Fish Agent. Custom voice + personality + opening line, and a real number. 🐟
Insane!!! You can now build a personal assistant with Grok Bot @bot + Fish Audio @FishAudio . > Calls you every day and updates you on your to-do list > Can take actions on your behalf (email people, set up meetings, add things to your calendar) > Takes <60 sec to set up Comment "Fish" and I'll share the template with you!
1
1
20
1,744
Fish Audio retweeted
Meet Creatify Max, the newest member of your ad team Everyone gets their own Max. It watches your accounts 24/7, writes the briefs, makes the videos, and launches the campaigns Max does the work. You make the call.
173
159
90
1,099
1,995,417
Congrats @nyn531 and the @Creatify_AI team on the Max agent launch 🎉 Proud to be powering the voice behind it.
Meet Creatify Max, the newest member of your ad team Everyone gets their own Max. It watches your accounts 24/7, writes the briefs, makes the videos, and launches the campaigns Max does the work. You make the call.
9
4
53
3,299
Before, a family practice’s after-hours calls went straight to voicemail. Now Ani, Skrypt Health’s AI receptionist, picks up first on every call, on Fish Audio voice. One month: 4,714 calls, 355 after-hours calls answered, ~190 staff hours back to the team. Full story 🐟 fish.audio/customers/?case=s…
7
1
1
33
2,485
Phone calls are the hardest test for a voice agent: pauses, interruptions, “mm-hmm.” That’s what our Live 3 full-duplex model is built for. Build a realtime voice agent with @AgentSkillNet's Voice Operator Agents skill, powered by Fish Audio. Live from Day 0. 🐟
Introducing the SkillNet × @FishAudio collab. We've partnered with Fish Audio, whose open-weight voice model has topped multiple benchmarks, to bring five powerful skills to SkillNet. Among them, Voice Operator Agents can run your business's phone line autonomously: answering calls in your chosen or cloned voice, grounded in your business's own data, screening for scams, and handling bookings and customer support.
10
5
1
65
8,477
Introducing Live 3: a full-duplex voice model built for real-time voice agents. No more awkward pauses on phone calls or getting interrupted mid-sentence by voice agents. It knows listening cues ("mm-hmm" and "ahan"), understands interruptions, and never cuts in between conversations. Use it here: s.fish.audio/yf7utj
Introducing @FishAudio Live 3: a full-duplex voice model that listens, says "mm-hmm," and knows when to shut up. Enterprise? Book a demo for your free custom agent: s.fish.audio/vxhgs6 Reply with your use case - we'll build it free for the first 1,000 people.
57
27
10
376
24,645
Fish Audio retweeted
Same tier as Tesla. Built on days of no sleep 🔥 So proud of my marketing team @FishAudio Every launch still feels like our first Same passion, same hype, every single time We never give up. We just keep shipping One more drops next week. Any guesses? 👀
Ranking the greatest launch videos of all time
8
3
1
60
4,371
Always good to see our models put to the test in real conversations! Thanks to @speko_ai for putting this benchmark together. 🐟
Replying to @FishAudio
@FishAudio transcribe-stream-1 posted the lowest error rate on real conversations of any model on Speko Benchmarks 11.5% word error rate across 60 speakers talking naturally, ahead of Qwen3-ASR, Inworld, ElevenLabs and OpenAI The top four are close, so it's a race worth watching
2
1
24
3,143
We gave our Realtime STT (Preview) 9 tongue twisters in 9 languages and kept speeding them up. Every caption is the raw output, word by word. No edits. Watch it 👇
14
4
3
100
7,278
A bigger stage. 🐟 Excited to team up and bring expressive AI voices to more builders and creators!
Drama 3 by @FishAudio is coming soon to Alibaba Cloud! With Drama 3, you can control how even a single word sounds, adjust its tone, and shift voices mid-sentence, bringing expressive AI voice generation to the next level! 🎙 We’re excited to support Fish Audio’s innovation and look forward to expanding our collaboration to unlock new possibilities for multimodal content creation.🚀
2
3
44
3,655
Fish Audio retweeted
Replying to @FishAudio
@FishAudio Transcribe Stream 1 just entered our speech-to-text leaderboard for accented English (22 real-time systems, 2,087 real learners, 16 accents) Watch where it lands.
3
2
37
2,912