Explore Audio Models

ACE-Step composes complete songs from text descriptions. Guide genre, mood, and structure with style tags and optional custom lyrics. Generates up to 4 minutes of multi-track audio with vocals.

≈ $0.050 per audio

ACE-Step 1.5 composes complete songs from text descriptions. Guide genre, mood, and structure with style tags and required custom lyrics. Generates up to 4 minutes of multi-track audio with vocals.

≈ $0.050 per audio

ACE-Step v1.5 Base is a Runware-hosted music model built for creator workflows, with stronger fidelity, more reliable stylistic consistency, and prompt-driven genre control for full-song generation.

≈ $0.009 per audio

ACE-Step v1.5 Turbo is the faster, lower-cost Runware variant for full-song generation, with broad genre coverage, improved stylistic consistency, and text-guided music creation for creator workflows.

≈ $0.006 per audio

Alibaba Fun-ASR Flash

Speech to Text

Alibaba Cloud DashScope non-realtime speech recognition with multilingual transcription, punctuation, and sentence/word timestamps.

≈ $0.004 per minute

ByteDance Seed Audio 1.0

Music

ByteDance Seed Audio 1.0 generates natural audio from text, with optional preset voices, up to three reference audio clips, or a single reference image.

≈ $300.06 per 1M characters (billed in 300-character blocks)

ByteDance Seed Speech TTS 2.0

Text to Speech

ByteDance Seed Speech TTS 2.0 for natural multilingual speech with voice instructions and delivery controls.

≈ $51.00 per 1M characters (billed in 1k-character blocks)

Demucs Stem Separation

Music

Separate up to 60 minutes / 700 MiB of stereo audio into vocals, drums, bass, guitar, piano, and other stems with fal Demucs.

≈ $0.023 per audio

ElevenLabs Scribe V1

Speech to Text

ElevenLabs Scribe V1 transcription with word-level timestamps and speaker identification

≈ $0.051 per minute

ElevenLabs Scribe V2

Speech to Text

ElevenLabs Scribe V2 transcription with improved accuracy, word-level timestamps, and speaker identification

≈ $0.051 per minute

ElevenLabs Turbo V2.5

Text to Speech

High quality with lowest latency, ideal for real-time applications. Supports 32 languages while maintaining natural voice quality.

≈ $102.00 per 1M characters

ElevenLabs v3

Text to Speech

High-quality text-to-speech with enhanced controls and natural voices.

≈ $170.00 per 1M characters

Gemini 2.5 Flash Preview TTS

Text to Speech

Google Gemini native TTS. Single and multi-speaker support via prompt.

≈ $51.17 per 1M characters

Gemini 2.5 Pro Preview TTS

Text to Speech

Higher-quality Gemini TTS with controllable style and tone.

≈ $102.17 per 1M characters

Gemini 3.1 Flash TTS Preview

Text to Speech

Google Gemini 3.1 Flash text-to-speech with inline audio tag and multi-speaker prompt support.

≈ $102.42 per 1M characters

Google Lyria 3 Pro Music

Music

Google Lyria 3 Pro generates premium music clips from a text prompt, with optional image guidance, negative prompts, and seed-based repeatability.

≈ $0.080 per audio

GPT-4o Mini Transcribe

Speech to Text

OpenAI's efficient speech-to-text model with improved accuracy over Whisper

≈ $0.005 per minute

GPT-4o Mini Transcribe (2025-03-20)

Speech to Text

Original release snapshot of GPT-4o Mini Transcribe

≈ $0.005 per minute