Navigation überspringen
Today, we're ending boring transcripts. Fish Audio’s ASR model now:
0:00 / 0:58

Today, we're ending boring transcripts. Fish Audio’s ASR model now:

Fish Audio

@FishAudio35.757 Follower

Auf X besuchen

44.945 Aufrufe

Today, we're ending boring transcripts. Fish Audio’s ASR model now: → Identifies different speakers → Understands what they're feeling → Labels emotion cues like [laughter], [surprised] in the transcript All this while supporting 83 languages and being the most accurate STT model out there. Try it out now 🐟

19 Kommentare

Kommentare aus dem Originalbeitrag auf X (Twitter)

  • Profilbild von OIiver

    @posedscaredcity

    Better than Meta muse transcribe?

    6 Likes

  • Profilbild von Fish Audio

    @FishAudio

    feel free to try out!

    1 Like

  • Profilbild von OIiver

    @posedscaredcity

    Ah it’s looking like it’s not streaming :(

  • Profilbild von Resona

    @resona_dev

    @soniox_ai I am certain your accuracy, especially for non English languages is far superior. However, this is a novel concept for adding significantly more context to transcribed speech. Hopefully we get something like this in Soniox v6.

    5 Likes

  • Profilbild von Sam

    @xiangyhu

    any plan to open source?

    3 Likes

  • Profilbild von Vishal Singh 🥑

    @vishalsingh2972

    Excited to try this ✨

    2 Likes

  • Profilbild von Mohammed

    @MoLearnAI

    I smell competition @ElevenLabs

    2 Likes

  • Profilbild von XXXTENTACIOFF

    @XXXTENTACIOFF2

    Not even close to @soniox_ai lol

    1 Like

  • Profilbild von Marsonal

    @revmarsonal

    is it free?

    1 Like

  • Profilbild von Adam Gera 亚当

    @AdamGera

    Make it cheaper.

  • Profilbild von JK | O ULTIMO PARDO | EDITOR

    @JohnnyKleber

    BY OPPUS 5.5

  • Profilbild von Chase Chick

    @RealChaseChick

    Awesome! Is this going to be integrated into the agents?

  • Profilbild von Kaylard - e/acc

    @KaylardAI

    We need benchmarks

  • Profilbild von Flix Muller

    @felix_muller_ai

    This is a big upgrade for transcripts. Speaker detection + emotion cues + 83 languages makes ASR much more useful for real conversations. 🔥

  • Profilbild von Daniel Priscu

    @daniel_priscu

    emotion labels in the transcript are going to make meeting notes a lot more awkward

  • Profilbild von JimRat

    @JimRatVideo

    Whats the open source plans?

  • Profilbild von Alex

    @aleexxx_ai

    Please add more languages and accuracy

  • Profilbild von Emmanuel

    @blackcoderx

    @grok what language do they support? Any aftican language

  • Profilbild von LastResort

    @LastResort48

    Price? @grok