# Text to speech and AI audio API

21 tools from fal.ai, from $0.002 per second.

## Capabilities

- [Text to speech (ElevenLabs)](/tools/audio-generation/text-to-speech.md): 6 tools, from $0.04 per 1,000 characters.
- [Speech to text](/tools/audio-generation/speech-to-text.md): 2 tools, from $0.008 per unit.
- [AI music](/tools/audio-generation/music.md): 3 tools, from $0.6 per minute.
- [Sound effects](/tools/audio-generation/sound-effects.md): 1 tool, from $0.002 per second.
- [Dubbing, voice changer & isolation](/tools/audio-generation/voice-tools.md): 3 tools, from $0.1 per unit.

## All 21 tools

- [ElevenLabs Eleven v3 expressive text to speech](/providers/fal/elevenlabs-tts-v3.md): `fal/elevenlabs-tts-v3`, $0.1 per 1,000 characters. Needs text. Served by fal.ai.
- [ElevenLabs Eleven v3 multi-speaker dialogue to speech text](/providers/fal/elevenlabs-text-to-dialogue-v3.md): `fal/elevenlabs-text-to-dialogue-v3`, $0.1 per 1,000 characters. Needs inputs. Served by fal.ai.
- [ElevenLabs Eleven v4 expressive text to speech](/providers/fal/elevenlabs-tts-v4.md): `fal/elevenlabs-tts-v4`, $0.08 per 1,000 characters. Needs text. Served by fal.ai.
- [ElevenLabs Eleven v4 Turbo fast text to speech](/providers/fal/elevenlabs-tts-v4-turbo.md): `fal/elevenlabs-tts-v4-turbo`, $0.04 per 1,000 characters. Needs text. Served by fal.ai.
- [ElevenLabs Multilingual v2 text to speech](/providers/fal/elevenlabs-tts-multilingual-v2.md): `fal/elevenlabs-tts-multilingual-v2`, $0.1 per 1,000 characters. Needs text. Served by fal.ai.
- [ElevenLabs Turbo v2.5 fast text to speech](/providers/fal/elevenlabs-tts-turbo-v2-5.md): `fal/elevenlabs-tts-turbo-v2-5`, $0.05 per 1,000 characters. Needs text. Served by fal.ai.
- [ElevenLabs Scribe speech to text](/providers/fal/elevenlabs-speech-to-text.md): `fal/elevenlabs-speech-to-text`, $0.03 per unit. Needs audio url. Served by fal.ai.
- [ElevenLabs Scribe v2 speech to text](/providers/fal/elevenlabs-scribe-v2.md): `fal/elevenlabs-scribe-v2`, from $0.008 per unit. Needs audio url. Served by fal.ai.
- [ElevenLabs Music text to music](/providers/fal/elevenlabs-music.md): `fal/elevenlabs-music`, $0.6 per minute. Takes output format, force instrumental, prompt and more, all optional. Served by fal.ai.
- [ElevenLabs Music v2](/providers/fal/elevenlabs-music-v2.md): `fal/elevenlabs-music-v2`, $0.6 per minute. Needs prompt and music length ms. Served by fal.ai.
- [ElevenLabs Music v2.5](/providers/fal/elevenlabs-music-v2-5.md): `fal/elevenlabs-music-v2-5`, $0.6 per minute. Needs prompt and music length ms. Served by fal.ai.
- [ElevenLabs Sound Effects v2 text to sound effect](/providers/fal/elevenlabs-sound-effects-v2.md): `fal/elevenlabs-sound-effects-v2`, $0.002 per second. Needs text. Served by fal.ai.
- [ElevenLabs Audio Isolation remove background noise](/providers/fal/elevenlabs-audio-isolation.md): `fal/elevenlabs-audio-isolation`, $0.1 per unit. Takes video url and audio url, all optional. Served by fal.ai.
- [ElevenLabs Dubbing translate and dub a video or audio](/providers/fal/elevenlabs-dubbing.md): `fal/elevenlabs-dubbing`, $0.6 per unit. Needs target lang. Served by fal.ai.
- [ElevenLabs Voice Changer speech to speech](/providers/fal/elevenlabs-voice-changer.md): `fal/elevenlabs-voice-changer`, $0.3 per unit. Needs audio url. Served by fal.ai.
- [ElevenLabs forced alignment](/providers/fal/elevenlabs-forced-alignment.md): `fal/elevenlabs-forced-alignment`, $0.22 per unit. Needs audio url and text. Served by fal.ai.
- [Gemini 3.8 Flash Lite TTS speech and two-speaker dialogue](/providers/fal/gemini-3-8-flash-lite-tts.md): `fal/gemini-3-8-flash-lite-tts`, $0.03 per 1,000 characters. Takes style instructions, voice, turns and more, all optional. Served by fal.ai.
- [Gemini 3.8 Flash TTS speech and two-speaker dialogue](/providers/fal/gemini-3-8-flash-tts.md): `fal/gemini-3-8-flash-tts`, $0.045 per 1,000 characters. Takes turns, style instructions, prompt and more, all optional. Served by fal.ai.
- [Grok voice](/providers/fal/xai-grok-voice.md): `fal/xai-grok-voice`, usage based, the maximum is shown before a run. Needs audio url. Served by fal.ai.
- [VEED clean audio](/providers/fal/veed-clean-audio.md): `fal/veed-clean-audio`, $0.0125 per unit. Removes background noise from speech while keeping quiet and distant words intact. Needs audio url. Served by fal.ai.
- [xAI text to speech](/providers/fal/xai-tts-v1.md): `fal/xai-tts-v1`, $0.015 per 1,000 characters. Needs text. Served by fal.ai.

## Related

- [AI video generation](/tools/video-generation.md): 93 tools, from $0.002 per second.

## Providers

- [fal.ai](/providers/fal.md): 214 tools, from $0.01 per call, some tools free.

## Questions

### Which models can my agent run?

Text to speech (ElevenLabs), speech to text, AI music, sound effects and dubbing, voice changer & isolation.

### Which providers serve AI audio tools?

fal.ai. Your agent compares them by price and inputs before it runs one.

### How is it billed?

Per call, at the provider's price with no markup, from $0.002 per second. Your agent sees the price before it runs a tool.

[Tools](/tools.md) · [Connection guide](/connect.md) · [Billing](/docs/billing.md)

---

[HTML page](/tools/audio-generation) · [Agent index](/llms.txt)
