Laporan Bug / Panggonan FiturLaporan Bug / Panggonan Fitur
Kloning Suara Pengubah Suara Narasi AI Dubbing AI Suara AI Chat Recorder Suara Celebrity Voice Generator Генератор смайликов Tambah →

AI Voice - Sesame CSM-1B

Penggunaan komersial OK 581 models Ora ana tandha banyu Ora perlu mlebu
Model:
+ GPT-5, Claude, Gemini
Mesin TTS Self-hosted Apache 2.0
Sesame CSM-1B — Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.
0 aksara ~0 tokens
Skala biaya karo jumlah aksara
Ngembangake basa...

Apa Sesame CSM-1B Apa swarane?

Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.

Di dieu, urang bisa maca: Hello, my name is Sam, and I am reading this sample to demonstrate the voice. - éta frasa demo TTS kanonikal.

Nalika gunakake Sesame CSM-1B

Buku Suara

Narasi panjang-bentuk kalawan nada konsisten. Tepek hiji bab dina hiji waktu, ngundeur minangka WAV atawa MP3, sarta stitch sacara luaran.

Podcast intros

Bukaan bumper pondok sarta ad-reads. Ngatur laju pikeun énergi, format-switch ka MP3 pikeun file anu langkung alit.

IVR + voicemail

Pangunjung sistem telepon. Output kualitas studio tanpa booking, rekaman, atawa NDAs kalawan talenta sora.

Kemampuan Ngakses

Tambah audio bareng karo isi ditulis kanggo para pamaca cacad pamahaman lan dyslexic. Drop-in ing kaca mana wae.

Frasa conto

"Welcome to the show, today we are exploring the future of AI."
"Your package has arrived. Please retrieve it from the front desk."
"Once upon a time, in a quiet village far away, lived a curious child."
"Press one for sales, two for support, or stay on the line for an agent."
"Breaking news: scientists have discovered a new species of deep-sea fish."
"Thank you for choosing us. We appreciate your business and look forward to serving you again."

Rencana

Generasi ditarik ti pool gratis anjeun sapopoé mimiti; sanggeus éta dijalankeun kaluar, pangiriman token dibayar dimimitian dina $5 → 200,000 token. Kacepetan ~5 token per karakter, minimum 100 per klip.

Referensi model lengkap → · Lihat kabeh swara TTS → · Ngbandingake2suara kang ana ing sisih →

Pilihan lanjutan
Hasil
Telung taun kepungkur. Ngundhuh token tambahan
Mau asil sing luwih apik? Premium model (GPT-5, Claude, Gemini) menehi kualitas sing luwih dhuwur. Papar rencana

❤️ Love Free.ai? Nyathet kanca-kancamu!

Signup pikeun meunangkeun tautan referensi sarta meunang 30,000 tokens per kabogoh.

Ingin luwih? Daftar gratis: 30,000 tokens / dina
Daftar Free

Nglakoni panjalukmu...

Sesame CSM-1B - Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio …

Cara Nggunakake AI Voice - Sesame CSM-1B

1
Ngetik inputmu

Ngetik teks, ngundhuh file, utawa gambaran apa sing sampeyan butuhake. Ora perlu akun.

2
Klik kanggo mbangun

AI urang ngaproses panjaluk anjeun dina detik nganggo model open-source anu pangsaéna.

3
Muat turun & Bagikan

Muter, salinan, utawa bagéan hasilmu. Bebas kanggo panggunaan pribadi lan komersial.

Gunake alat iki liwat API

Otomatisasi alat ieu ti kode anjeun sorangan. OpenAI-kompatibel REST titik akhir, Bearer-token otentikasi, teu perlu SDK tambahan. Token biaya cocog antarmuka web.

Dokumen API Njupuk Kunci API 
curl -X POST https://api.free.ai/v1/tts/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from Free.ai", "voice": "af_heart", "model": "kokoro"}'

Kabeh Free AI Tools

Kloning Suara
Pengubah Suara
Narasi AI
Dubbing AI
Suara AI Chat
Recorder Suara
Celebrity Voice Generator
Генератор смайликов

AI Voice - Sesame CSM-1B - FAQ

Sesame CSM-1B ngadukung loba basa. Daftar anu bener gumantung kana mesin; formulir dina halaman ieu nampi teks naon waé sarta mesin bakal ngahasilkeun dina basa anu didukung. Lihat /voice/ pikeun milih multi-engine lengkep lamun peryogi basa husus.

Kabéh mesin ngahasilkeun basa Inggris Amerika netral sacara piawai sarta aksen anu cocog pikeun wewengkon pikeun basa non-Inggris. Mesin Premium bisa ngajelaskeun variasi aksen - lebetkeun conto pikeun ngabandingkeun.

Dukungan SSML béda-béda gumantung kana mesin. Tag pause, prosody, jeung emphasis dihormat dina kabéh mesin premium sarta dina sababaraha mesin self-hosted. Teks biasa salawasna mampuh - teu merta merta.

Streaming TTS aya dina mesin premium ngaliwatan /v1/tts/ API endpoint kalawan stream=true. Web UI dina halaman ieu balikkeun klip pinuh sanggeus rendering réngsé.

Sesame CSM-1B dijalankeun dina GPUs urang sorangan. Generasi drawing ti pool bébas anjeun sapopoé kahiji. Sanggeus dileungitkeun, tokens dibayar dimimitian dina $5 → 200,000 tokens. Kacepetan ~5 tokens per karakter, minimum 100 per clip.

Dina 5000 karakter per pancén dina UI web. Pikeun bagian anu langkung lami (buku audio, bab lengkep), nganggo /voice/audiobook/ anu otomatis ngagulung sareng ngagiling, atanapi ngahubungi API dina loop.

Ya - POST daftar string ka /v1/tts/batch/, atawa nganggo UI ruang kerja di /workspace/ pikeun ngahijikeun TTS kana pipa anu langkung panjang (contona, translate → speak → stitch).

Ya - POST teks ka /v1/tts/ kalawan model="Sesame CSM-1B" (atawa slug dina kaca ieu). Ngulang WAV atawa MP3. Lihat /api/ kanggo referensi lengkap + snippet SDK.

Halaman ieu nyaéta teks-ka-wacana, lain kloning sora - sora nyaéta piawai mesin. Pikeun kloning sora (ngunggah audio referensi), tingali /voice/clone/, anu meryogikeun anjeun gaduh hak sora atanapi ngadaptarkeun idin anu dituliskeun.

Mesin self-hosted dijalankeun dina GPU Free.ai-dipikawanoh; teu aya anu ninggalkeun server urang. Mesin premium ngaliwatan teks ka upstream model panyadia di handapeun DPA urang. Kami teu latihan dina input anjeun sarta teu ngajual data.

Ya - Free.ai ngawenangkeun pamakéan komersial tina audio anu dihasilkeun. Lisénsi mesin anu di handapeun (Apache 2.0, MIT, atawa istilah vendor) digambarkeun di luhur sarta dina halaman referensi model; dina praktekna ieu hartosna voiceover, iklan, podcast, sarta aplikasi sadayana aya dina scope.

Ya - tugas gagal dipulangkeun sacara otomatis ka sumber (pool saben dinten atanapi token dibayar). Upami dipulangkeun henteu muncul dina dinten anu sami, kirimkeun surel ka contact@free.ai.

Daftar gratis: 30,000 tokens / dina

Akun Free

Kartu kredit ora dibutuhake

Kepiye sampeyan ngitung alat iki?

4.6/5 from 5 ratings

Love Free.ai? Nyathet kanca-kancamu!