05/23/2026
Major API expansion — new Music Generation, Audio Enhancement, and additional audio processing endpoints are now available. The API reference has been fully restructured with updated endpoint paths.
- Speech to Text: Transcribe audio or video files with optional speaker diarization and word-level timestamps (
POST /v1/audio/stt). - Podcast Generation: Generate multi-speaker AI podcasts from scripts or prompts (
POST /v1/audio/podcastgen). - Dubbing: Automatically dub audio and video into another language while preserving the original voice (
POST /v1/audio/dubbinggen). - Voice Design: Design a custom AI voice from a text prompt and preview it instantly (
POST /v1/voice/design). - Music Generation: Generate full music tracks with lyrics, style, and reference tracks — supports model versions
v3andr2(POST /v1/music/musicgen). - Music Generation by Prompt: Generate music from a text prompt with control over style and duration (
POST /v1/music/musicgenbyprompt). - Music Cover: Create AI voice covers of songs using any available voice model, with support for multi-singer configurations (
POST /v1/music/cover). - Audio Enhancement Suite: Nine dedicated audio enhancement endpoints — Speech Enhancement, Super Resolution (8 kHz → 48 kHz), Speaker Separation, Remove Mouth Sounds, Remove Long Silences, Filler Word Detection, Filler Word Removal, Stuttering Removal, and Audio Normalization.
- Process Pipeline: All-in-one enhancement pipeline combining any combination of the above enhancement steps in a single request (
POST /v1/enhancer/process/pipeline). - Updated all existing endpoint paths to the new versioned routes (e.g.
/v1/audio/*,/v1/voice/*,/v1/task/*).
10/10/2025
A new update that enhances stability, adds Text to Speech character pack purchases, and improves the Blog and Guide experience.
- Improved overall stability and performance with multiple bug fixes.
- Added support for Text-to-Speech character pack purchases.
- Fixed scroll-following behavior in the Blog and Guide side navigation.
- Resolved issues with recommended content display in Blog and Guide sections.
25/09/2025
FineVoice 3.0 (beta) is here with a brand-new upgrade! Experience faster text-to-speech generation and expressive Emotion Tags for more natural results. With the all-new AI Voice Design, you can create and customize unique voices in just seconds. Now offering 1,500+ AI voices across 154 languages, FineVoice empowers creators in media, entertainment, education, and business to produce diverse and personalized voices effortlessly.
- Text Emotion Control: Fine-tune emotional expression for storytelling, advertising, or voiceovers—making your content truly engaging and authentic.
- Royalty Free Sound Effects: Generate unique, copyright-free sound effects from text and video input for any project-enjoy complete creative freedom with no licensing concerns.
- Instant Voice Cloning: Clone any voice in just seconds for use in text-to-speech or voice transformation, streamlining your creative process.
- Custom AI Voice Design: Create personalized AI voices and generate unique voiceovers for your content, characters,or brand-enjoy maximum flexibility and creative control.
- Practical Tools & Solutions: Access a versatile suite of advanced AI voice tools — including an AI Voice Changer, AI Voice Enhancer, Speech to Text, and AI Podcast Generator — delivering simple, efficient, and highly adaptable solutions for any project.
- 154+ Multi-Language Support: Create custom Al voices in 154 global languages and accents, expanding your reach to diverse audiences.
03/01/2025
The update brings an improved UI, bug fixes, and the new Video to Sound Effects feature.
- Improve UI: The interface is optimized and upgraded to bring a better experience.
- Fix Bug: Some bugs on certain features have been fixed.
- Add New Feature: FineVoice Video to Sound Effects feature is now live.
08/20/2024
The latest update introduces credits for rewards, the new FineVoice TTS V2 model for more natural and expressive voices, additional commercial voices, and various bug fixes to enhance the user experience.
01/11/2024
In this update, FineVoice introduces enhanced natural voices, expanded AI voice models, improved AI voice changing and cloning, faster transcription, and seamless audio extraction.