Explore Audio Models

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.

≈ $0.102 per audio

ElevenLabs v3

Text to Speech

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

≈ $0.170 per audio

Inworld flagship TTS model with the best balance of quality and speed, plus enhanced alignment data.

≈ $0.020 per audio

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.

≈ $0.102 per audio

GPT-4o Mini TTS (2025-12-15)

Text to Speech

Latest snapshot of GPT-4o Mini TTS with voice instructions support

≈ $0.013 per audio

Studio-quality HD text-to-speech with expressive delivery, emotion control, pronunciation customization, and fine-grained audio controls for production-ready speech.

≈ $0.170 per audio

Gemini 2.5 Flash Preview TTS

Text to Speech

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

≈ $0.051 per audio

GPT-4o Mini TTS

Text to Speech

Ultra-low cost text-to-speech model with voice instructions support

≈ $0.013 per audio

OpenAI TTS

Text to Speech

Standard quality text-to-speech model with low latency

≈ $0.025 per audio

Kokoro 82M

Text to Speech

High-quality multilingual text-to-speech model

≈ $0.002 per audio

Qwen 3 TTS 1.7B

Text to Speech

Bring speech to your texts using Qwen3-TTS with pre-trained voices or cloned voice embeddings.

≈ $0.120 per audio

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

MiniMax Music Cover transforms a reference song into a new style while preserving the core melody. Provide a style prompt plus an MP3 URL for the source track.

≈ $0.150 per audio

Generate songs with Mureka v9 through WaveSpeed. Priced per generated song.

≈ $0.030 per audio

Whisper Large V3

Speech to Text

OpenAI's state-of-the-art speech recognition model

≈ <$0.001 per minute

ACE-Step composes complete songs from text descriptions using Wavespeed’s music foundation model. 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

Affordable Runware-hosted xAI text-to-speech with five voices, inline expressive controls, and multilingual auto-detection.

≈ $0.017 per audio

Stable Audio 3 Medium

Music

Stable Audio 3 Medium generates high-quality stereo music up to 6 minutes from text prompts, trained on fully licensed data for commercial use.

≈ $0.041 per audio

MAI-Transcribe 1.5

Speech to Text

Microsoft fast transcription model with automatic language detection, punctuation, and 100+ BCP-47 locales.

≈ $0.010 per minute

GPT-4o Mini Transcribe

Speech to Text

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

≈ $0.005 per minute

Ultra-Fast, Ultra-Human, Ultra-Smart TTS with <250ms latency, natural voice cloning, seamless multilingual support across 40+ languages, and industry-leading text normalization for flawless, expressive communication.

≈ $0.170 per audio

OpenAI TTS HD

Text to Speech

High definition text-to-speech model with superior quality

≈ $0.051 per audio

GPT-4o Mini Transcribe (2025-12-15)

Speech to Text

Latest snapshot of GPT-4o Mini Transcribe with improved accuracy

≈ $0.005 per minute

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

Gemini 2.5 Pro Preview TTS

Text to Speech

Higher-quality Gemini TTS with controllable style and tone.

≈ $0.102 per audio

MAI-Voice-2

Text to Speech

Microsoft high-fidelity expressive text-to-speech with multilingual MAI-Voice-2 prebuilt voices.

≈ $0.037 per audio

Whisper-1

Speech to Text

OpenAI's original Whisper model with full format support including SRT and VTT subtitles

≈ $0.010 per minute

Eleven Music is a studio‑grade text‑to‑music model. Generate music with natural‑language prompts in any style — perfect for game soundtracks, podcast backgrounds, and marketing reels. Control genre, style, and structure, with optional vocals or instrumental. Supports 10–300s MP3 with selectable sample rate and bitrate.

≈ $0.100 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

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